diff --git a/.gitattributes b/.gitattributes
index 2b6b188a846c5c3a3805dc5176651da80aa33775..6ff2941b2da4a52b40140d295416f89665884c81 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -40,3 +40,9 @@ meta-llama-3-8b-instruct-grpo-concept-enhanced/global_step_24/actor/huggingface/
meta-llama-3-8b-instruct-grpo-concept-enhanced/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-1.5b-grpo-concept-enhanced/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-1.5b-grpo-concept-enhanced/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_24_3418ed7b521e43cf829daa26d6d4a0d9.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_24_3418ed7b521e43cf829daa26d6d4a0d9.json
new file mode 100644
index 0000000000000000000000000000000000000000..57b0fce04809a7ba6beccedd94da26ee8811399e
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_24_3418ed7b521e43cf829daa26d6d4a0d9.json
@@ -0,0 +1,28 @@
+{
+ "null": [
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5
+ ]
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_48_77edb149e79a41bab8042c10feead348.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_48_77edb149e79a41bab8042c10feead348.json
new file mode 100644
index 0000000000000000000000000000000000000000..baa585d367d6df6cb788a1a20600151e619979fd
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_48_77edb149e79a41bab8042c10feead348.json
@@ -0,0 +1,52 @@
+{
+ "null": [
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5
+ ]
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_72_f7963851c8d044afb37829634ef63e72.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_72_f7963851c8d044afb37829634ef63e72.json
new file mode 100644
index 0000000000000000000000000000000000000000..82ec43b8f8d94a3fdadabe7b8641db60c561566b
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_72_f7963851c8d044afb37829634ef63e72.json
@@ -0,0 +1,76 @@
+{
+ "null": [
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5
+ ]
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_24_f94a922bf5fb4ffe94486f2f83aaeb61.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_24_f94a922bf5fb4ffe94486f2f83aaeb61.json
new file mode 100644
index 0000000000000000000000000000000000000000..9418976609daf8a9bdb4f36ba4fb922edcb8f9e3
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_24_f94a922bf5fb4ffe94486f2f83aaeb61.json
@@ -0,0 +1,28 @@
+{
+ "null": {
+ "1": 0.5,
+ "2": 0.5,
+ "3": 0.5,
+ "4": 0.5,
+ "5": 0.5,
+ "6": 0.5,
+ "7": 0.5,
+ "8": 0.5,
+ "9": 0.5,
+ "10": 0.5,
+ "11": 0.5,
+ "12": 0.5,
+ "13": 0.5,
+ "14": 0.5,
+ "15": 0.5,
+ "16": 0.5,
+ "17": 0.5,
+ "18": 0.5,
+ "19": 0.5,
+ "20": 0.5,
+ "21": 0.5,
+ "22": 0.5,
+ "23": 0.5,
+ "24": 0.5
+ }
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_48_5b235ec2e0c549d5a059b8c62750cdfe.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_48_5b235ec2e0c549d5a059b8c62750cdfe.json
new file mode 100644
index 0000000000000000000000000000000000000000..c4fc349833f21f1bf76658a9f49a88cee6d34351
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_48_5b235ec2e0c549d5a059b8c62750cdfe.json
@@ -0,0 +1,52 @@
+{
+ "null": {
+ "1": 0.5,
+ "2": 0.5,
+ "3": 0.5,
+ "4": 0.5,
+ "5": 0.5,
+ "6": 0.5,
+ "7": 0.5,
+ "8": 0.5,
+ "9": 0.5,
+ "10": 0.5,
+ "11": 0.5,
+ "12": 0.5,
+ "13": 0.5,
+ "14": 0.5,
+ "15": 0.5,
+ "16": 0.5,
+ "17": 0.5,
+ "18": 0.5,
+ "19": 0.5,
+ "20": 0.5,
+ "21": 0.5,
+ "22": 0.5,
+ "23": 0.5,
+ "24": 0.5,
+ "25": 0.5,
+ "26": 0.5,
+ "27": 0.5,
+ "28": 0.5,
+ "29": 0.5,
+ "30": 0.5,
+ "31": 0.5,
+ "32": 0.5,
+ "33": 0.5,
+ "34": 0.5,
+ "35": 0.5,
+ "36": 0.5,
+ "37": 0.5,
+ "38": 0.5,
+ "39": 0.5,
+ "40": 0.5,
+ "41": 0.5,
+ "42": 0.5,
+ "43": 0.5,
+ "44": 0.5,
+ "45": 0.5,
+ "46": 0.5,
+ "47": 0.5,
+ "48": 0.5
+ }
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_72_4bad72bbf8c94237a324c33022c66204.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_72_4bad72bbf8c94237a324c33022c66204.json
new file mode 100644
index 0000000000000000000000000000000000000000..806ea08c7d3820f02df37ecfe2d468c2e245443b
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/acc_step_with_step_72_4bad72bbf8c94237a324c33022c66204.json
@@ -0,0 +1,76 @@
+{
+ "null": {
+ "1": 0.5,
+ "2": 0.5,
+ "3": 0.5,
+ "4": 0.5,
+ "5": 0.5,
+ "6": 0.5,
+ "7": 0.5,
+ "8": 0.5,
+ "9": 0.5,
+ "10": 0.5,
+ "11": 0.5,
+ "12": 0.5,
+ "13": 0.5,
+ "14": 0.5,
+ "15": 0.5,
+ "16": 0.5,
+ "17": 0.5,
+ "18": 0.5,
+ "19": 0.5,
+ "20": 0.5,
+ "21": 0.5,
+ "22": 0.5,
+ "23": 0.5,
+ "24": 0.5,
+ "25": 0.5,
+ "26": 0.5,
+ "27": 0.5,
+ "28": 0.5,
+ "29": 0.5,
+ "30": 0.5,
+ "31": 0.5,
+ "32": 0.5,
+ "33": 0.5,
+ "34": 0.5,
+ "35": 0.5,
+ "36": 0.5,
+ "37": 0.5,
+ "38": 0.5,
+ "39": 0.5,
+ "40": 0.5,
+ "41": 0.5,
+ "42": 0.5,
+ "43": 0.5,
+ "44": 0.5,
+ "45": 0.5,
+ "46": 0.5,
+ "47": 0.5,
+ "48": 0.5,
+ "49": 0.5,
+ "50": 0.5,
+ "51": 0.5,
+ "52": 0.5,
+ "53": 0.5,
+ "54": 0.5,
+ "55": 0.5,
+ "56": 0.5,
+ "57": 0.5,
+ "58": 0.5,
+ "59": 0.5,
+ "60": 0.5,
+ "61": 0.5,
+ "62": 0.5,
+ "63": 0.5,
+ "64": 0.5,
+ "65": 0.5,
+ "66": 0.5,
+ "67": 0.5,
+ "68": 0.5,
+ "69": 0.5,
+ "70": 0.5,
+ "71": 0.5,
+ "72": 0.5
+ }
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_24_cfab2ce305ae4276a5db0667244773e6.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_24_cfab2ce305ae4276a5db0667244773e6.json
new file mode 100644
index 0000000000000000000000000000000000000000..c6efa220e0231e4fe68901223dc58f9a71560fbc
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_24_cfab2ce305ae4276a5db0667244773e6.json
@@ -0,0 +1,7 @@
+{
+ "math_mcq": {
+ "0": 0.5855855855855856,
+ "10": 0.5675675675675675,
+ "20": 0.5585585585585585
+ }
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_48_8298c2d63cf84ce8bc5364b9605243fc.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_48_8298c2d63cf84ce8bc5364b9605243fc.json
new file mode 100644
index 0000000000000000000000000000000000000000..5549aeb645babb04cba3ae436e40a86f10798768
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_48_8298c2d63cf84ce8bc5364b9605243fc.json
@@ -0,0 +1,9 @@
+{
+ "math_mcq": {
+ "0": 0.5855855855855856,
+ "10": 0.5675675675675675,
+ "20": 0.5585585585585585,
+ "30": 0.5945945945945946,
+ "40": 0.5405405405405406
+ }
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_72_299940a224b74e2891e365ed571206df.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_72_299940a224b74e2891e365ed571206df.json
new file mode 100644
index 0000000000000000000000000000000000000000..30656e58b5c624401c1c808c13935f9cd9b0b84a
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/accuracy/val_acc_source_with_step_72_299940a224b74e2891e365ed571206df.json
@@ -0,0 +1,12 @@
+{
+ "math_mcq": {
+ "0": 0.5855855855855856,
+ "10": 0.5675675675675675,
+ "20": 0.5585585585585585,
+ "30": 0.5945945945945946,
+ "40": 0.5405405405405406,
+ "50": 0.5405405405405406,
+ "60": 0.5855855855855856,
+ "70": 0.6486486486486487
+ }
+}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/chat_template.jinja b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "layer_types": [
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention"
+ ],
+ "max_position_embeddings": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/extra_state_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2499ea08db831e54fe750cede4e5893e7880f375
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/extra_state_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3962d6b53b998d4df9a6567f3d304b47743d0172742f330c198a5eb5d2f0a760
+size 14632
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/extra_state_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..858f2986667566ded9b59a934556773dc083fc85
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/extra_state_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d81daaaec05685d6bc01a566df61d28191e5e7642f3a2a2404904a93b92c6e
+size 14632
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/generation_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/generation_config.json
@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 151646,
+ "eos_token_id": 151643,
+ "pad_token_id": 151643,
+ "transformers_version": "4.55.4"
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/chat_template.jinja b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "layer_types": [
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention"
+ ],
+ "max_position_embeddings": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/special_tokens_map.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model-00001-of-00002.safetensors b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7bfad699e3dc4fd1354ca1a2ee2f4e3b5f1d88ec
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f8dd4e48d119db16324772f25ed1a30608fb25d95dec8007d4e12445f2ebfc
+size 4996670464
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model-00002-of-00002.safetensors b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0bc9c94ff6cd7202eabbb863635da33b9b559320
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f380d64761592bafb25dcb5d35b2b1be4ea61d17b228d9c6fead09ab8c339d0f
+size 2111719976
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model.safetensors.index.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+ "metadata": {
+ "total_parameters": 888544000,
+ "total_size": 7108352000
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c7dbe4d03114c38ed5b672c893acc31330cdcc3b
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9023986fb9c822bafadf78e88b64ef785dd6afcde44752427a673c414577667b
+size 3554364602
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97feacd4a1d7c623fefb0638d6631b9157da65b0
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00918f6059eb6ebbdf92e0e77e5c66813ab244d577c5553f6a8c3292f48489d4
+size 3554364602
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/optim_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f23d20ed3ec7c35a726c63fa78b47a81a6f54ea5
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/optim_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f999b52df04b6e0ff53ad1ed60fea223c6cf2b49568eb77b179463cd879679
+size 7108378739
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/optim_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..747ff6bfa8615657f35012da2e5611432de2071c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd88706cc91b0f8b0f45d58119a9cda1fb84e211cfdf895bc7e6b1cfabeb86f
+size 7108378739
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/special_tokens_map.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/data.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bb9ef95e3602226ac6663f33fec9357d9c1ec722
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3adc30950e92556e672d48265a0c6e030a3867af92c61c493906822e2b379c
+size 6948493
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/training_state.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c9ad8f985be86fba5bcfadbcb8cbcc26199ff224
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5]}, "history_accuracy_with_step": {"null": {"1": 0.5, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.5, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.5, "13": 0.5, "14": 0.5, "15": 0.5, "16": 0.5, "17": 0.5, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.5, "23": 0.5, "24": 0.5}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5855855855855856, "10": 0.5675675675675675, "20": 0.5585585585585585}}}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/chat_template.jinja b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "layer_types": [
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention"
+ ],
+ "max_position_embeddings": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/extra_state_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ec49117e806be5b5b00dcc1ba22a8a6f8b78a5f8
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/extra_state_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b2fd0ab4e4ac2aadb3d441949c1cbe633ffba6c57529c040c45f9c78558d818
+size 14632
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/extra_state_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dedbd483c0a24292ad32128d93d07d832f62ac4a
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/extra_state_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d31e055a650ee0c369ca764c5a1b8a6872ff2c4c22c31642fbf2564f33a103c
+size 14632
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/generation_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/generation_config.json
@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 151646,
+ "eos_token_id": 151643,
+ "pad_token_id": 151643,
+ "transformers_version": "4.55.4"
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/chat_template.jinja b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "layer_types": [
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention"
+ ],
+ "max_position_embeddings": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/special_tokens_map.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model-00001-of-00002.safetensors b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ff012ab9925b275f8338d08786bbc1e732680032
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68bbc2bd7a608b7ba75a7b4145353b026d1a75e753b467435d79f0e9c836944
+size 4996670464
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model-00002-of-00002.safetensors b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cc6c7e5d1c76d3765c5438107e90c391d356d753
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a0c4ba6fa22e1fd6a62a10c9f7a84c5c10557b7c42c841628ef29a27fe0551
+size 2111719976
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model.safetensors.index.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+ "metadata": {
+ "total_parameters": 888544000,
+ "total_size": 7108352000
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2b86b190b774c687ba2671afa771bbf9da1f96c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9224e1855d09a951f0e9ab05f4f5938bda062c01adbdff38728bfc2e37c499d2
+size 3554364602
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..73b5cd41d2eb2cfd7da695e2a7bb51003c417b26
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b01f2e8e210f40645fe7e68e3697cb98401aa1398481e0a110899d6dad5e4fb
+size 3554364602
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/optim_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ce487129427c773a6aad6fa36e927e089cb59221
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/optim_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16fd6da3000a6859b47560f5a6a28ea2949cdae4a898480040ebb47fc78fd69
+size 7108378739
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/optim_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c723086f0f69180e9cd982ace6c427749ed1e2ab
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b253a14dcdad5d3536e490379ba6c1ec72766b23d4352594616cef430b89e4c7
+size 7108378739
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/special_tokens_map.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/data.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2060d758febf404fab718a76d303b839c5b0c003
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deadada4e14cffeb8fa749641d20a3652f4e8bbc2bd6fa40c3032047c9c74d70
+size 6948493
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/training_state.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..8eb3bcf4169d954d06b16210c36db3cf7399a540
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5]}, "history_accuracy_with_step": {"null": {"1": 0.5, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.5, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.5, "13": 0.5, "14": 0.5, "15": 0.5, "16": 0.5, "17": 0.5, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.5, "23": 0.5, "24": 0.5, "25": 0.5, "26": 0.5, "27": 0.5, "28": 0.5, "29": 0.5, "30": 0.5, "31": 0.5, "32": 0.5, "33": 0.5, "34": 0.5, "35": 0.5, "36": 0.5, "37": 0.5, "38": 0.5, "39": 0.5, "40": 0.5, "41": 0.5, "42": 0.5, "43": 0.5, "44": 0.5, "45": 0.5, "46": 0.5, "47": 0.5, "48": 0.5}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5855855855855856, "10": 0.5675675675675675, "20": 0.5585585585585585, "30": 0.5945945945945946, "40": 0.5405405405405406}}}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/chat_template.jinja b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "layer_types": [
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention"
+ ],
+ "max_position_embeddings": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/extra_state_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c507e8b17d59a06769fd3092241d0f5e51a9ae93
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/extra_state_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c94446a47c1ede2806185dfb38a67ae8bcc1112db1c46725d417c675686efc
+size 14632
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/extra_state_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..477a6edb887bb30e3ea469eef7aaa0227abe6600
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/extra_state_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53eea3acabd25a7ac580b9b6c6a01c8a60d769680bcac625f0ee90e7ef15a359
+size 14632
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/generation_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/generation_config.json
@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 151646,
+ "eos_token_id": 151643,
+ "pad_token_id": 151643,
+ "transformers_version": "4.55.4"
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/chat_template.jinja b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "layer_types": [
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention",
+ "full_attention"
+ ],
+ "max_position_embeddings": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/special_tokens_map.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model-00001-of-00002.safetensors b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0fe926e1a4d597c856fb4009dc070aa840dc1275
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4f10a5a3961cab3c637ff91bc0ed7116a7c75116cb5f492426282826f8f80a
+size 4996670464
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model-00002-of-00002.safetensors b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d9678e6372b0a07420a72c67636221031c83049a
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa339b4920abcc6b658207ec99690df431ee0091b4dc1f7b97f97deaa1f8b8d
+size 2111719976
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model.safetensors.index.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+ "metadata": {
+ "total_parameters": 888544000,
+ "total_size": 7108352000
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f9e8755b92cb3353d4b5f4ba7aa4acb4126054de
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0e6b5d633ab48f5e8548c4f2847f16f7ed5bd3f23994cad5e4a7d505c760bd
+size 3554364602
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..41a9d8d3ae02be613c65a8eb1ce025b071e39158
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79865f47152e251b30eaf17fddb65eef7f0d3c65b4a7fde1502a7dcdb6f97f5
+size 3554364602
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/optim_world_size_2_rank_0.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ed13d870fd679a05311eebf5df9ad5e7897a49b7
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/optim_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a839279e2bdd2d87524e858b3fd317ce788551e4c79ce4f9a4ffbb8d7fc5577b
+size 7108378739
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/optim_world_size_2_rank_1.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6431710091e606b84cc0d57450f9408493d783f8
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35d721bb526b2707ac43a7f3515eafba7ce029abd49a0284b8a2abca4b4eb5e
+size 7108378739
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/special_tokens_map.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer_config.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/data.pt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..828b12f4ddd5fdbd37b9594b0bb54a524a09cc55
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f772a46c4ad13212c319576680a8d025aff7420153dd57a0fb259c3e801f08
+size 6948493
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/training_state.json b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a0da3dbf0f554ff5c142dbcc5a7ab62d614d2f2
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5]}, "history_accuracy_with_step": {"null": {"1": 0.5, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.5, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.5, "13": 0.5, "14": 0.5, "15": 0.5, "16": 0.5, "17": 0.5, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.5, "23": 0.5, "24": 0.5, "25": 0.5, "26": 0.5, "27": 0.5, "28": 0.5, "29": 0.5, "30": 0.5, "31": 0.5, "32": 0.5, "33": 0.5, "34": 0.5, "35": 0.5, "36": 0.5, "37": 0.5, "38": 0.5, "39": 0.5, "40": 0.5, "41": 0.5, "42": 0.5, "43": 0.5, "44": 0.5, "45": 0.5, "46": 0.5, "47": 0.5, "48": 0.5, "49": 0.5, "50": 0.5, "51": 0.5, "52": 0.5, "53": 0.5, "54": 0.5, "55": 0.5, "56": 0.5, "57": 0.5, "58": 0.5, "59": 0.5, "60": 0.5, "61": 0.5, "62": 0.5, "63": 0.5, "64": 0.5, "65": 0.5, "66": 0.5, "67": 0.5, "68": 0.5, "69": 0.5, "70": 0.5, "71": 0.5, "72": 0.5}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5855855855855856, "10": 0.5675675675675675, "20": 0.5585585585585585, "30": 0.5945945945945946, "40": 0.5405405405405406, "50": 0.5405405405405406, "60": 0.5855855855855856, "70": 0.6486486486486487}}}
\ No newline at end of file
diff --git a/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/latest_checkpointed_iteration.txt b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/latest_checkpointed_iteration.txt
new file mode 100644
index 0000000000000000000000000000000000000000..9cd72aa941214d4cb8522dda34eb12cf878e3e8b
--- /dev/null
+++ b/models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/latest_checkpointed_iteration.txt
@@ -0,0 +1 @@
+72
\ No newline at end of file