Update README.md

README.md

@@ -6,4 +6,37 @@ base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 tags:
 - code
----
+---
+
+# LogicCoder-8B
+
+**LogicCoder-8B** is a 8B-parameter language model fine-tuned for code generation tasks. It is based on the DeepSeek-R1-Distill-Llama-8B model and trained on a Python subset of the open-r1/codeforces-cots dataset.
+
+This model was fine-tuned on pruned CoTS examples derived via our **ASAP** method(**A**nchor-guided, **S**urpris**a**l-polished **P**runing), focusing on highly compressed yet semantically informative reasoning traces.
+
+# 🧠 Reasoning Mode
+
+We recommend **explicitly activating reasoning mode by inserting ```<think>``` in the prompt**.
+
+# 🔧 Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("azzzacs/LogicCoder-8B", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("azzzacs/LogicCoder-8B", device_map="auto", trust_remote_code=True).eval()
+
+message = [{"role": "user", "content": "Please write a Python quick sort algorithm.\n"}]
+prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False) + "<｜Assistant｜><think>\n"
+
+model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=4096,
+    do_sample=False,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+print(tokenizer.decode(outputs[0][len(model_inputs.input_ids[0]):], skip_special_tokens=False))
+```