Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

EXPORT_INFO.json

@@ -0,0 +1,10 @@
+{
+  "source_run": "gb200_30B_w4a4_FFN_FSDP_repro0403_0613",
+  "source_step": 620,
+  "source_actor": "/lustre/fsw/general_sa/shuazhang/python_space/verl_for_nvfp4_20251031/verl_w4a4_perf/ckpts/DAPO-NVFP4-QAT/gb200_30B_w4a4_FFN_FSDP_repro0403_0613/global_step_620/actor",
+  "source_training_mode": "w4a4_ffn_qat",
+  "export_format": "huggingface_bf16",
+  "exported_at_utc": "2026-07-06T15:40:45Z",
+  "slurm_job_id": "2332259",
+  "slurm_array_task_id": "8"
+}

EXPORT_VALIDATION.json

@@ -0,0 +1,23 @@
+{
+  "status": "passed",
+  "model_type": "qwen3_moe",
+  "architecture": "Qwen3MoeForCausalLM",
+  "safetensors_shards": 13,
+  "indexed_tensors": 18867,
+  "safetensors_bytes": 61066577912,
+  "tensor_payload_bytes": 61064245248,
+  "tensor_dtypes": [
+    "BF16"
+  ],
+  "checks": [
+    "required HF metadata present",
+    "Qwen3-MoE config recognized",
+    "all indexed shards present and non-empty",
+    "every safetensors header readable",
+    "header keys exactly match index mapping",
+    "all tensors are BF16",
+    "keys and shapes exactly match native Qwen3-MoE architecture",
+    "index total_size matches BF16 tensor payload",
+    "total model size in expected range"
+  ]
+}

SHA256SUMS

@@ -0,0 +1,25 @@
+6ef0a31a2f83b5bd0bee4f63e34c0bae464df1304dab1c7d2acea1302279cf68  ./EXPORT_INFO.json
+0b4932c84885058dc167b775556df2a7e782e0ff187ab4a8d4712e00c2be4ce4  ./EXPORT_VALIDATION.json
+c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680  ./added_tokens.json
+87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5  ./chat_template.jinja
+b2cb93e208b29512ada352824c4dd8df139a7d9f486e0efd493ca69d87460960  ./config.json
+ed20652a673ea86443a2342d11daeed5e2bf51891cca56e95dac39c5f3843793  ./generation_config.json
+8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5  ./merges.txt
+87a2edc5412e06c9f6ce4ac59fef4a6998d9ca684ff496a81d735d4ebca00722  ./model-00001-of-00013.safetensors
+829ef9d2eb73c9d86dc35fc050d0fe11e638f70d7af227e9586af9cf1a2d198e  ./model-00002-of-00013.safetensors
+908f6ed1b8ba8730d1f2954f83febc1d6afbbcb0aba672c1d88581f1325d50e0  ./model-00003-of-00013.safetensors
+6d9822371c95a97492fe277a3cb06fbd187f291974f49d05d475491d67c00134  ./model-00004-of-00013.safetensors
+9abb01d06dceb6738dc9689c2e646e27d8d94d3823bc01ab84879054e7cea367  ./model-00005-of-00013.safetensors
+70c5a7857dbaab79d5a776eff8217439fb3f7c025f3c14549c935fbacbc7856e  ./model-00006-of-00013.safetensors
+edb37d1cf338e7d4fdf52ec73a8589d377278a35eae9ee44eb148d12c5fa45d4  ./model-00007-of-00013.safetensors
+a21f017974a16f6afb0a0565629619770e07749a255199b6ad60b0e539d8178a  ./model-00008-of-00013.safetensors
+47993017e1054c708b5fbd1dd9762716251c174dfcac5535ca5c4d3a87365d51  ./model-00009-of-00013.safetensors
+37ef0c8205211fd61aed1422eea22a044abcdc57269a76fe9de25393f7d8b67d  ./model-00010-of-00013.safetensors
+4f7de10b102d618cd18eb9fa22a4d011d323394bc951e6cd250100b7e0f5538b  ./model-00011-of-00013.safetensors
+dce0276f3ba7491edf5454079a56b8f07905cd0646c3cd174b0caedc1d5a05c4  ./model-00012-of-00013.safetensors
+a2b02661881acb0073107aef7bbe9979db5daaf79645a19c70f6b23f51ba578e  ./model-00013-of-00013.safetensors
+290765bd09a362c40c00a4a579710e3df189f42b722357d9983d8d83ed4602f2  ./model.safetensors.index.json
+6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9  ./special_tokens_map.json
+c0acdaba32b920d640afb36af4396c91974e074735636e4016d17a8ed9c03730  ./tokenizer.json
+bfe8be339767100a9ef64a50e2b923197db919efe90b1d3637eb0cb34d92ff15  ./tokenizer_config.json
+ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910  ./vocab.json

_SUCCESS

@@ -0,0 +1,4 @@
+completed_at_utc=2026-07-06T15:42:43Z
+run=gb200_30B_w4a4_FFN_FSDP_repro0403_0613
+step=620
+manifest_sha256=0c9372faa7816ad6e0f9b79403d2d2d5bf743fc6fd0fe78f59caa0a282f3d814

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 151643,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a2edc5412e06c9f6ce4ac59fef4a6998d9ca684ff496a81d735d4ebca00722
+size 4999315016

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829ef9d2eb73c9d86dc35fc050d0fe11e638f70d7af227e9586af9cf1a2d198e
+size 4999845968

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908f6ed1b8ba8730d1f2954f83febc1d6afbbcb0aba672c1d88581f1325d50e0
+size 4729299792

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9822371c95a97492fe277a3cb06fbd187f291974f49d05d475491d67c00134
+size 4998759072

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abb01d06dceb6738dc9689c2e646e27d8d94d3823bc01ab84879054e7cea367
+size 4999869232

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c5a7857dbaab79d5a776eff8217439fb3f7c025f3c14549c935fbacbc7856e
+size 4997208040

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb37d1cf338e7d4fdf52ec73a8589d377278a35eae9ee44eb148d12c5fa45d4
+size 4998256568

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21f017974a16f6afb0a0565629619770e07749a255199b6ad60b0e539d8178a
+size 4997223952

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47993017e1054c708b5fbd1dd9762716251c174dfcac5535ca5c4d3a87365d51
+size 4999312312

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ef0c8205211fd61aed1422eea22a044abcdc57269a76fe9de25393f7d8b67d
+size 4998796432

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7de10b102d618cd18eb9fa22a4d011d323394bc951e6cd250100b7e0f5538b
+size 4998759184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce0276f3ba7491edf5454079a56b8f07905cd0646c3cd174b0caedc1d5a05c4
+size 4999309928

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b02661881acb0073107aef7bbe9979db5daaf79645a19c70f6b23f51ba578e
+size 1350622416

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0acdaba32b920d640afb36af4396c91974e074735636e4016d17a8ed9c03730
+size 11422753

tokenizer_config.json

@@ -0,0 +1,243 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 2048,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}