Update README.md

README.md

@@ -1,16 +1,80 @@
 ---
-library_name: transformers
-pipeline_tag: text-generation
 tags:
-  - text-generation
   - medical
   - loRA
   - 4bit
-base_model: deepseek-ai/DeepSeek-V2-Lite
+  - conversational
+pipeline_tag: text-generation
 ---
 
 # DeepSeek-V2-medical
 
+This repository contains a 4-bit LoRA adapter fine-tuned on top of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) for **medical treatment planning**.
+
+- **Base model**: `deepseek-ai/DeepSeek-V2-Lite` (4-bit quantized)  
+- **Adapter**: LoRA, trained on clinical vignette → treatment plan pairs  
+- **Tokenizer**: same as base, with `pad_token` set to `eos`
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, BitsAndBytesConfig
+from peft         import PeftModel
+import torch
+
+# 1) Load tokenizer + adapter
+tokenizer = AutoTokenizer.from_pretrained(
+    "CodCodingCode/DeepSeek-V2-medical",
+    trust_remote_code=True
+)
+tokenizer.pad_token_id = tokenizer.pad_token_id or tokenizer.eos_token_id
+
+bnb = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.float16,
+)
+
+# 2) Reload the base quantized model
+from transformers import AutoModelForCausalLM
+base = AutoModelForCausalLM.from_pretrained(
+    "deepseek-ai/DeepSeek-V2-Lite",
+    quantization_config=bnb,
+    device_map="auto",
+    trust_remote_code=True,
+)
+base.resize_token_embeddings(len(tokenizer))
+
+# 3) Attach your LoRA adapter
+model = PeftModel.from_pretrained(
+    base,
+    "CodCodingCode/DeepSeek-V2-medical",
+    device_map="auto",
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+)
+model.config.use_cache = False  # match your training config
+
+# 4) Generate
+prompt = (
+    "### Instruction:\n"
+    "You are a board-certified clinician ...\n\n"
+    "### Input:\n"
+    "THINKING: ...\n\n"
+    "### Response:\n"
+)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.2,
+    top_p=0.95,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id,
+)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
 This repository contains a 4-bit LoRA fine-tuned adapter on top of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) for medical treatment planning.
 
 ## Model Card