Upload folder using huggingface_hub

.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

README.md

@@ -1,3 +1,112 @@
----
-license: gemma
----
+# Gemma-3-12B-GRPO trained with GRPO via LoRA
+
+Due to limited available computational resources, we randomly sampled 500 data points from MedQA-USMLE using a methodology and conducted preliminary GRPO experiments with LoRA using the [Unsloth](https://github.com/unslothai/unsloth) framework. We are now releasing this as a preview version. More experiments and explorations are currently underway, and a technical report is in preparation. Thank you for your patience. We conduct the experiments on one RTX-A6000 Ada (48GB VRAM).
+
+## Evaluation Results
+
+The model is evaluated on four benchmark datasets: MMLU, MMLU-Pro, CMMU, GSM8K, GPQA. The experimental results are summarized in Table 1, with comprehensive analyses provided in the Detailed Results section.
+
+<center><strong>Tab.1 Evaluation results.</strong></center>
+
+| Dataset | Gemma-3-12b-it | Gemma3-12b-GRPO |
+| :-----: | :------------: | :-------------: |
+|  MMLU   |     65.51      |     70.13      |
+|  MMLU-Pro   |     60.17      |     59.99      |
+|  CMMLU   |     54.81     |     57.07     |
+|  GSM8K   |     91.58     |     91.81     |
+|  GPQA   |     34.98     |     34.23     |
+
+## Requirements
+
+```shell
+pip install torch==2.6.0 torchaudio==2.6.0 torchvision==0.21.0 -i --index-url https://download.pytorch.org/whl/cu124
+pip install transformer vllm bitsandbytes peft
+pip install flash-attn --no-build-isolation
+```
+
+## Run with vLLM
+
+You can use the following script to run with vLLM.
+
+```shell
+vllm serve qiuxi337/gemma-3-12b-it-grpo \
+     --gpu-memory-utilization 0.85 \
+     --max-model-len 4096 \
+     --served-model-name gemma3-12b-grpo \
+     --api-key your_api_key
+```
+
+## Detail Results
+
+### MMLU
+
+![mmlu](asserts/mmlu.png)
+
+**Fig.1 The results on the MMLU benchmark.**
+
+![MMLU_Humanities](asserts/mmlu_humanities.png)
+
+**Fig.2  The results on the MMLU-Humanities**
+
+![MMLU_Social_Science](asserts/mmlu_social_science.png)
+
+**Fig.3  The results on the MMLU-Social Science**
+
+![MMLU_STEM](asserts/mmlu_stem.png)
+
+**Fig.4  The results on the MMLU-STEM**
+
+![MMLU_others](asserts/mmlu_other.png)
+
+**Fig.5  The results on the MMLU-Other**
+
+### MMLU-Pro
+
+![MMLU_Pro](asserts/mmlu_pro.png)
+
+**Fig.6  The results on the MMLU-Pro**
+
+### CMMLU
+
+![cmmlu](asserts/cmmlu.png)
+
+**Fig.7  The results on the CMMLU benchmark.**
+
+![CMMLU_Humanities](asserts/cmmlu_humanities.png)
+
+**Fig.8  The results on the CMMLU-Humanities**
+
+![CMMLU_Social_Science](asserts/cmmlu_social_science.png)
+
+**Fig.9  The results on the CMMLU-Social Science**
+
+![CMMLU_STEM](asserts/cmmlu_stem.png)
+
+**Fig.10  The results on the CMMLU-STEM**
+
+![CMMLU_others](asserts/cmmlu_other.png)
+
+**Fig.11  The results on the CMMLU-Other**
+
+![CMMLU_China_Specific](asserts/cmmlu_china_specific.png)
+
+**Fig.12  The results on the CMMLU-China Specific**
+
+## Acknowledge
+
+[Gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it)
+
+[Unlsoth](https://github.com/unslothai/unsloth)
+
+## Citation
+
+```ini
+@software{Qiu_Open-Medical-R1,
+author = {Qiu, Zhongxi and Zhang, Zhang and Hu, Yan and Li, Heng and Liu, Jiang},
+license = {MIT},
+title = {{Open-Medical-R1}},
+url = {https://github.com/Qsingle/open-medical-r1},
+version = {0.1}
+}
+```
+

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\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    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "hidden_size": 3840,
+    "intermediate_size": 15360,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "sliding_window": 1024
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.50.3"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6668b99ed6da08969919188f2424f3f730d540b7c0dacc1a16a4f68ada3d4ad2
+size 4979901696

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb69fa7ea887baa742d6596fe01afb2e5d41057c1c35858409286d53e69b21ba
+size 4931296448

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69bdd8ccb6271053b1ee6886b2993287add8482fce935700882270262f971bcb
+size 4931296512

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a812453801a1ec4b47b9b87147a64cd78186dfdcb2e894405dd5f316527e2728
+size 4931296512

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5292328709b6f1d95db6d1c3b6ba89a6d64ca4397bc3ad852010a5e775d10a14
+size 4601000792

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef
+size 33384722

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074