pratimassaravanan/clinical-sft-grpo

.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

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+model_name: grpo
+tags:
+- generated_from_trainer
+- trl
+- grpo
+- hf_jobs
+licence: license
+---
+
+# Model Card for grpo
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="pratimassaravanan/grpo", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+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: 5.6.2
+- Pytorch: 2.11.0
+- 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}
+}
+```

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "sft_grpo_output/sft_merged",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29a7525c24c574ecd715ee2061f2c80256b6764561aa4965aa1fa44808f5942
+size 69782384

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 %}

completions/completions_00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89ed229ae2ba8e749fc5965516a11fba04bed49f747e8e1aed1091afbb40c1e
+size 23953

completions/completions_00002.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6a7fda894fd35bc157c58451a575bd0a2ec4816d9c68291206e80bd8dcddf3
+size 23972

completions/completions_00003.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41b0301b6c319d58c98dbef17a5ca81c067e41219c87478a3c2ed8c19620049
+size 24575

completions/completions_00004.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aea417f2ea1786053e76f57f5a6ef7e6f9e37aec995491dc1e2ea7dd0d7ab50
+size 24332

completions/completions_00005.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93806f3dfe01ff7118fa3fa4007b6150d28f26c5381b9d48d4bb8ba40ac75003
+size 23110

completions/completions_00006.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d88d4fa9b71f6586d2849791b51c4123d598892f302d55027e3129fca4d1cd2
+size 25275

completions/completions_00007.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee2acf1e212135efe16720b369d14b6a77dcd1ded24f3c959ed34561e3c5d9f
+size 25318

completions/completions_00008.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c9cce308146f2e99404379068c37ff434e123ed43d58d4aafee4324dee8d57
+size 22879

completions/completions_00009.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b1fc0548ab019a01c3b30e489270664a1601efddbd4b0c12f49b9662d96649
+size 24363

completions/completions_00010.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d7aebd5ab48389a3ea82a78a658336511e86a83b17eab3eeae6f3151f1d3422
+size 24266

completions/completions_00011.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508383d561f41ec9a9d11071b16677e16b8956f78fbcab4ca13d9a9b91b391ff
+size 24695

completions/completions_00012.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0aff78cdc01cfa5ad0a869af61bf7f68232130c3e4e3a4209967db2e23d6fd
+size 24129

completions/completions_00013.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c732fddec3e09b662e192a6b1127fae7ad1ad7b171fb1aabcc9dd63cc6e1cd92
+size 27701

completions/completions_00014.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ef5f93e41406b354c3b392c3e7e1ee7ae87832e549335182ea4d627c88d64b
+size 22875

completions/completions_00015.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8426e559e1af61f60d4cc0daccee5190289bc50e0f81930d1a19b4c3b80e0ac
+size 27296

completions/completions_00016.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fd23ebe02152ae00e7c5d4bf091cc289e551fb66df7600872af57663114236
+size 23062

completions/completions_00017.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdfc0eb2b4414399cc1567a91c03b1830d487601a2287fb3c8f6f85f543b2a4
+size 22819

completions/completions_00018.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdb634a56501dc1db07af228cc8db56b36736270e48b4c26e42f81a2a0f25b8
+size 23445

completions/completions_00019.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ea8c67fad80088ff3d8ed3489c6205070144805fa90ab9feadd57bb8e249b3
+size 23787

completions/completions_00020.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22f3836114e422c3c9f2556dec78cc09f2c0c0b09d1817c86ef95fa658eef85
+size 24823

completions/completions_00021.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50ed7690682dbc5005f1aa01954948caed9554af03bf0c7ffdf1304b6b77a31
+size 23536

completions/completions_00022.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2d8ecb6f303774d0a238b3baea9ff39291a763d7ac8b5214e37f366b1095de
+size 23383

completions/completions_00023.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2020eee35a5eaff972f4e863b0debb7b85a224d3eba9fe0c86217a4a0747e298
+size 23485

completions/completions_00024.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649c6a8c37727181b062e5c7e1b8d27c417a67f624e1d61b711ba5c410dc07ce
+size 23534

completions/completions_00025.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed8693d1089ee8383b4b149f7888d3a190ec63e594a1a04785b0a030f19e2e5
+size 23570

completions/completions_00026.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a696763a52bb47af705d5286eaa2865ff5c33fdfdd243de3aa2f0b25ef32465
+size 27418

completions/completions_00027.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa250936eb7544cc5b87709c2cdfd625f53c6ae2dc49c3ef89398ab207a2b5e
+size 23329

completions/completions_00028.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f3eaadcac000ab19ff458bb871586b804accfd0fe3697d0e54bf244e6df702
+size 25480

completions/completions_00029.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ce80793d6d684d3de6929efb2201743656740f1231af0c1b0c250c21803dbd
+size 25212

completions/completions_00030.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7973f77f7c8750fd752e592cb20941c73ebd24b114c1bc4ddb195a1ad2f3a8
+size 24641

completions/completions_00031.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba74959b212cb5ce64679891cdd7f2d61ca309a8aa64d3f99fe7b13cf8c53559
+size 23250

completions/completions_00032.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e383b66ee252c182cf17ba29f2c00cb63a32761fbc5490f3693fec299ed6882
+size 23384

completions/completions_00033.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abef387a920a74f37534385ac584675e66db90bf29d2c0e12aed5a149f03efe
+size 27803

completions/completions_00034.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c3349373ab2699f6f6304c361f7d1dc7aaa21d3a8c9598d7b46fa72be5b660
+size 23366

completions/completions_00035.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4505ab990b9e77a9ab852cc8d588091fe366eb8267326597b9d9988fd6f5e1e7
+size 23525

completions/completions_00036.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2c7a7b7c79a980dcb68e14fcab0292ca9b020c9fa38301bf31618eb1a051d9
+size 23628

completions/completions_00037.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b30237e94e8838541be95135f1850b4a94aee5c9dad859ff9fff15f29438bbe
+size 23293

completions/completions_00038.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d29c7cfb8d79ccdbdf473f22ddcac8153c557ab25bb288e85ade8b9f9baa10
+size 23161

completions/completions_00039.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01be2f43e17adbd85fffe1f9b323fa508aeb0a636dab29005304791bfa03f162
+size 23648

completions/completions_00040.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c62da03708b45b76e7d747a635c6d6a1294667a38cebab4777a22a9a061bd01
+size 23551

completions/completions_00041.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3091f29c9247770c7316a5910be5a6eb3eebe7c86ed1b7c3e6bcbf96e3b1b8a0
+size 23625

completions/completions_00042.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8b6d174a086f0253892f4c5552172d04889cd1c2af1a417995fda603041721
+size 23378

completions/completions_00043.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c87b9246be0d5268fdf60d1b1e739f8a52da03b72e0b526e5ebdb9c39d4900
+size 23335

completions/completions_00044.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5600d1b29ab78d74d9217377dbf59ff8b9039b50547276ecf1078478f8ce580
+size 24461

completions/completions_00045.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd1a484c727a08a4889275ef177b720f8e9437dae7478765b7f44927e32a4ee
+size 23669