Update README.md

README.md

@@ -1,6 +1,7 @@
 ---
 base_model: openai/gpt-oss-20b
-datasets: kingabzpro/gpt-oss-20b-medical-qa
+datasets:
+- FreedomIntelligence/medical-o1-verifiable-problem
 library_name: transformers
 model_name: gpt-oss-20b-medical-qa
 tags:
@@ -8,6 +9,10 @@ tags:
 - trl
 - sft
 licence: license
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
 ---
 
 # Model Card for gpt-oss-20b-medical-qa
@@ -18,19 +23,46 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 
 ```python
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
 
-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="kingabzpro/gpt-oss-20b-medical-qa", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-20b")
 
-## Training procedure
+# Load the original model first
+model_kwargs = dict(attn_implementation="eager", torch_dtype="auto", use_cache=True, device_map="auto")
+base_model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b", **model_kwargs).cuda()
+
+# Merge fine-tuned weights with the base model
+peft_model_id = "kingabzpro/gpt-oss-20b-medical-qa"
+model = PeftModel.from_pretrained(base_model, peft_model_id)
+model = model.merge_and_unload()
 
- 
+question = dataset[0]["Open-ended Verifiable Question"]
+
+text = render_infernce_harmony(question)
+
+inputs = tokenizer(
+    [text + tokenizer.eos_token], return_tensors="pt"
+).to("cuda")
+outputs = model.generate(
+    input_ids=inputs.input_ids,
+    attention_mask=inputs.attention_mask,
+    max_new_tokens=20,
+    eos_token_id=tokenizer.eos_token_id,
+    use_cache=True,
+)
+response = tokenizer.batch_decode(outputs)
+print(response[0])
+```
+Output:
 
+```bash
+<|start|>developer<|message|># Instructions
 
+You are a medical expert with advanced knowledge in clinical reasoning and diagnostics. Respond with ONLY the final diagnosis/cause in ≤5 words.<|end|><|start|>user<|message|>An 88-year-old woman with osteoarthritis is experiencing mild epigastric discomfort and has vomited material resembling coffee grounds multiple times. Considering her use of naproxen, what is the most likely cause of her gastrointestinal blood loss?<|end|><|start|>assistant<|return|><|message|>Stomach ulcer<|end|><|return|>
+```
+## Training procedure
 This model was trained with SFT.
 
 ### Framework versions
@@ -39,21 +71,4 @@ This model was trained with SFT.
 - Transformers: 4.55.2
 - Pytorch: 2.8.0.dev20250319+cu128
 - Datasets: 4.0.0
-- Tokenizers: 0.21.4
-
-## Citations
-
-
-
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+- Tokenizers: 0.21.4