Initial

README.md

@@ -50,19 +50,58 @@ please read the [CONTRIBUTING](CONTRIBUTING.md) first._
 #### Hugging Face
 
 ```python
-from datasets import load_dataset
-
-# 141k:
-dataset_141k = load_dataset("bunyaminergen/cornstack-python-v1-filtered", revision="v3", split="train")
-print(dataset_141k[0])
-
-# 282k:
-dataset_282k = load_dataset("bunyaminergen/cornstack-python-v1-filtered", revision="v5", split="train")
-print(dataset_282k[0])
-
-# 423k:
-dataset_423k = load_dataset("bunyaminergen/cornstack-python-v1-filtered", revision="v7", split="train")
-print(dataset_423k[0])
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
+model_name = "bunyaminergen/Qwen2.5-Coder-1.5B-Instruct-SFT"
+
+quant_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    quantization_config=quant_config,
+    device_map="auto"
+)
+
+model.eval()
+
+messages = [
+    {"role": "system", "content": "You are a senior Python developer."},
+    {"role": "user", "content": "Give me a quick example of bubble sort in Python."}
+]
+
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+max_new_tokens = 512
+temperature = 0.9
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        do_sample=True,
+        top_p=0.95,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+print(result)
 ```
 
 ---