(Trained with Unsloth)

chat_template.jinja

@@ -1,8 +1,70 @@
-{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{'<start_of_turn>user
-' + messages[0]['content'] | trim + ' ' + messages[1]['content'] | trim + '<end_of_turn>
-'}}{% set messages = messages[2:] %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<start_of_turn>user
-' + message['content'] | trim + '<end_of_turn>
-'}}{% elif message['role'] == 'assistant' %}{{'<start_of_turn>model
-' + message['content'] | trim + '<end_of_turn>
-' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model
-' }}{% endif %}
+{{ bos_token }}{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+{%- set thinking = enable_thinking is defined and enable_thinking -%}
+{%- set loop_messages = messages -%}
+{%- if messages[0]['role'] in ['system', 'developer'] or thinking -%}
+    {{ '<|turn>system
+' }}
+    {%- if thinking -%}
+        {{ '<|think|>
+' }}
+    {%- endif -%}
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {{ messages[0]['content'] | trim }}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {{ '<turn|>
+' }}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<|turn>' + role + '
+' }}
+    {%- if message['content'] is string -%}
+        {%- if role == "model" -%}
+            {{ strip_thinking(message['content']) }}
+        {%- else -%}
+            {{ message['content'] | trim }}
+        {%- endif -%}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'audio' -%}
+                {{ '<|audio|>' }}
+            {%- elif item['type'] == 'image' -%}
+                {{ '<|image|>' }}
+            {%- elif item['type'] == 'video' -%}
+                {{ '<|video|>' }}
+            {%- elif item['type'] == 'text' -%}
+                {%- if role == "model" -%}
+                    {{ strip_thinking(item['text']) }}
+                {%- else -%}
+                    {{ item['text'] | trim }}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<turn|>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<|turn>model
+'}}
+{%- endif -%}

config.json

@@ -7,8 +7,11 @@
     "attn_logit_softcapping": 50.0,
     "bos_token_id": 2,
     "cache_implementation": "hybrid",
-    "torch_dtype": "float16",
-    "eos_token_id": 1,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": [
+        1,
+        107
+    ],
     "final_logit_softcapping": 30.0,
     "head_dim": 256,
     "hidden_act": "gelu_pytorch_tanh",
@@ -55,8 +58,7 @@
     "rope_scaling": null,
     "rope_theta": 10000.0,
     "sliding_window": 4096,
-    "transformers_version": "4.57.2",
-    "unsloth_version": "2025.11.1",
+    "unsloth_version": "2024.9",
     "use_cache": true,
     "vocab_size": 256000
 }

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    1,
+    1,
+    107
+  ],
+  "max_length": 8192,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.2"
+}

special_tokens_map.json

@@ -1,6 +1,34 @@
 {
-  "bos_token": "<bos>",
-  "eos_token": "<end_of_turn>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a6ecc0c8b61e4f65249a9da9cf0809371813500854cfee2848a793cbdfb19b
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
 size 34362873

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -11,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": "<end_of_turn>",
+      "content": "<eos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -859,7 +859,7 @@
       "special": true
     },
     "107": {
-      "content": "<eos>",
+      "content": "<end_of_turn>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1995,13 +1995,21 @@
       "special": false
     }
   },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<end_of_turn>",
+  "eos_token": "<eos>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "tokenizer_class": "GemmaTokenizerFast",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
-  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{'<start_of_turn>user\n' + messages[0]['content'] | trim + ' ' + messages[1]['content'] | trim + '<end_of_turn>\n'}}{% set messages = messages[2:] %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<start_of_turn>user\n' + message['content'] | trim + '<end_of_turn>\n'}}{% elif message['role'] == 'assistant' %}{{'<start_of_turn>model\n' + message['content'] | trim + '<end_of_turn>\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model\n' }}{% endif %}"
+  "use_default_system_prompt": false,
+  "chat_template": "{{ bos_token }}{%- macro strip_thinking(text) -%}\n    {%- set ns = namespace(result='') -%}\n    {%- for part in text.split('<channel|>') -%}\n        {%- if '<|channel>' in part -%}\n            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n        {%- else -%}\n            {%- set ns.result = ns.result + part -%}\n        {%- endif -%}\n    {%- endfor -%}\n    {{- ns.result | trim -}}\n{%- endmacro -%}\n{%- set thinking = enable_thinking is defined and enable_thinking -%}\n{%- set loop_messages = messages -%}\n{%- if messages[0]['role'] in ['system', 'developer'] or thinking -%}\n    {{ '<|turn>system\n' }}\n    {%- if thinking -%}\n        {{ '<|think|>\n' }}\n    {%- endif -%}\n    {%- if messages[0]['role'] in ['system', 'developer'] -%}\n        {{ messages[0]['content'] | trim }}\n        {%- set loop_messages = messages[1:] -%}\n    {%- endif -%}\n    {{ '<turn|>\n' }}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<|turn>' + role + '\n' }}\n    {%- if message['content'] is string -%}\n        {%- if role == \"model\" -%}\n            {{ strip_thinking(message['content']) }}\n        {%- else -%}\n            {{ message['content'] | trim }}\n        {%- endif -%}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'audio' -%}\n                {{ '<|audio|>' }}\n            {%- elif item['type'] == 'image' -%}\n                {{ '<|image|>' }}\n            {%- elif item['type'] == 'video' -%}\n                {{ '<|video|>' }}\n            {%- elif item['type'] == 'text' -%}\n                {%- if role == \"model\" -%}\n                    {{ strip_thinking(item['text']) }}\n                {%- else -%}\n                    {{ item['text'] | trim }}\n                {%- endif -%}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<turn|>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<|turn>model\n'}}\n{%- endif -%}\n"
 }