初始化项目，由ModelHub XC社区提供模型

Model: agarwalanu3103/clarify-rl-grpo-qwen3-0.6b Source: Original Platform
2026-06-16 07:28:16 +08:00
commit 0ee2064163
34 changed files with 427 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: transformers
+model_name: clarify-rl-grpo-qwen3-0.6b
+tags:
+- generated_from_trainer
+- trackio:https://agarwalanu3103-clarify-rl-grpo-qwen3-0.6b.hf.space?project=huggingface&runs=agarwalanu3103-1777125583&sidebar=collapsed
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for clarify-rl-grpo-qwen3-0.6b
+
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="agarwalanu3103/clarify-rl-grpo-qwen3-0.6b", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+[<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" width="150" height="24"/>](https://agarwalanu3103-clarify-rl-grpo-qwen3-0.6b.hf.space?project=huggingface&runs=agarwalanu3103-1777125583&sidebar=collapsed)
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 1.2.0
+- Transformers: 5.7.0.dev0
+- Pytorch: 2.8.0
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{shao2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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 %}
--- a/completions/completions_00001.parquet
+++ b/completions/completions_00001.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0e2f0205d68fc37b562516c3e4be1ca39b8b1607a24c2ade9e1c2022537686
+size 21398
--- a/completions/completions_00002.parquet
+++ b/completions/completions_00002.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252d37328d1450e421502770ff06b47314533ab418722a9704bf1a4811f2d30d
+size 19642
--- a/completions/completions_00003.parquet
+++ b/completions/completions_00003.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3aaf9579d8b5adaadc038f94ec38cc11e433aabd1ced082ad212c7b2e8fe55a
+size 23735
--- a/completions/completions_00004.parquet
+++ b/completions/completions_00004.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa6593f1dc3b7ba455483b0cb7122a04726fe85aa9432b68c6d16b244116fec
+size 22691
--- a/completions/completions_00005.parquet
+++ b/completions/completions_00005.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fa2294ddd294bfe2d69e9d1b06999a491e31238dac72c79ac9fad41de26c19
+size 19000
--- a/completions/completions_00006.parquet
+++ b/completions/completions_00006.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ead937347295b71e7798a0bc8e325ae70fec3f79a3e8e08a81d50e147b6f848
+size 18725
--- a/completions/completions_00007.parquet
+++ b/completions/completions_00007.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a2dbde1a0b341f859bee29d6986d99c95df8ff8fd34cd89af76300a5e14526
+size 18769
--- a/completions/completions_00008.parquet
+++ b/completions/completions_00008.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4d30b76aaeceb3cba2fff488256777107a30281baada7709a71c8410ba019a
+size 18679
--- a/completions/completions_00009.parquet
+++ b/completions/completions_00009.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e234f8e86ba7fee6c37f1f0430e3e5573950d3f437f3a5a9090714851b236aa
+size 22702
--- a/completions/completions_00010.parquet
+++ b/completions/completions_00010.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3073df678a878733b86f576d04b8d72cd02f0bf9f0a5ad8c734740fd05ec4a98
+size 18848
--- a/completions/completions_00011.parquet
+++ b/completions/completions_00011.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef67e22041518598eb133b39bba514d954c9728b1674236a896e6f26f41a86ff
+size 18675
--- a/completions/completions_00012.parquet
+++ b/completions/completions_00012.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c113e2355c1f6db02a6448c1599e8b7ca2b2c55aa7166ff56c4b076f400f9b15
+size 18661
--- a/completions/completions_00013.parquet
+++ b/completions/completions_00013.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b0b83a3db6134e129ec2c0f9033559b36da92e253c7ae5a513e95af43558ae
+size 18323
--- a/completions/completions_00014.parquet
+++ b/completions/completions_00014.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5346599ba073570f760c076c952c877266763e4debe2778dfb3c608372c81096
+size 17862
--- a/completions/completions_00015.parquet
+++ b/completions/completions_00015.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7164d22d00ec20deecbf3d3c44713de177fcf54fa6d94fc23f802a94aaabf106
+size 18282
--- a/completions/completions_00016.parquet
+++ b/completions/completions_00016.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28e961a1b330d37b3fa3ace0af4ebd6ece684b1bdfb2f7dc2c663ef54d380e7
+size 17597
--- a/completions/completions_00017.parquet
+++ b/completions/completions_00017.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61db3ed935a8f8be67920cef02e2bfe52534155e102f299e0a39db600ec9abf
+size 19165
--- a/completions/completions_00018.parquet
+++ b/completions/completions_00018.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00505b73b3f79b19b21d417bd8385611d7cca06e968b413dfd3b3c8d72ab32c
+size 17821
--- a/completions/completions_00019.parquet
+++ b/completions/completions_00019.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37281337833344875d50d95165f7df77f932a8b0d16b4c139e186d233da3378
+size 18833
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759a1f8a09d94917983c17146c497c9ae6be4cf3d11fab2f5175e97a099aa723
+size 18733
--- a/completions/completions_00021.parquet
+++ b/completions/completions_00021.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f117c6b26e3081316689b0f8e03d1b2f83485fef695a0a165f93e5678d81e067
+size 20075
--- a/completions/completions_00022.parquet
+++ b/completions/completions_00022.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f7041eee0fabc8053994ecc856c2e37f50bc57eb40e622f02fd67aa93d946b
+size 18158
--- a/completions/completions_00023.parquet
+++ b/completions/completions_00023.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944c192a834253dd0b5c29346ef476ccf5a726e0c601140df00e91f810a2cc11
+size 18678
--- a/completions/completions_00024.parquet
+++ b/completions/completions_00024.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c28b631321e8db227969dba90a9310e5fe572ed1d3523892fc1f2dfea5905b
+size 18585
--- a/completions/completions_00025.parquet
+++ b/completions/completions_00025.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b7829b5cb6ec7995b55b4d23d11595324d45962212ac638ece0629cf0eee9f
+size 19017
--- a/config.json
+++ b/config.json
@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.7.0.dev0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041d632f60e15c70a3558f498e26e88333240ec899e1e8ee01f6f16b7dde4ce9
+size 2384234968
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,75 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "reasoning_content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object",
+          "x-parser": "json",
+          "x-parser-args": {
+            "transform": "{type: 'function', function: @}"
+          }
+        },
+        "type": "array",
+        "x-regex-iterator": "<tool_call>\\s*(.+?)\\s*</tool_call>"
+      }
+    },
+    "type": "object",
+    "x-regex": "^(?:<think>\\n?(?:(?P<reasoning_content>.*?\\S.*?)\\n?|[\\s]*)</think>\\s*)?(?P<content>.*?)(?:\\n(?=<tool_call>))?(?=(?:<tool_call>|<\\|im_end\\|>|$))(?P<tool_calls>(?:<tool_call>.+?</tool_call>\\s*)+)?\\s*(?:<\\|im_end\\|>|$)"
+  },
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2479197fade7488de2ad269a8ff9a249648bf24e49f7872fe58c5da209596429
+size 7185