Tuhin20/CodeLlama-7b-Instruct-FineTuned-JavaPython

1 2# 🧠 CodeLlama-7B-Instruct Fine-Tuned on Java + Python3 4This model is a fine-tuned version of **codellama/CodeLlama-7b-Instruct-hf**, 5trained using **Unsloth** on a curated dataset of **85k Python and Java programming tasks**.6 7## ⚙️ Technical Details8- Framework: Unsloth + TRL SFTTrainer  9- Quantization: QLoRA (4-bit, merged into Q4_K_M GGUF)  10- Context length: 2048 tokens  11- Base model: `CodeLlama-7b-Instruct-hf`12 13## 🧩 Files14- `config.json`15- `tokenizer.model`16- `CodeLlama-7b-Instruct-hf.Q4_K_M.gguf`17 18## 🪄 Example Usage19```python20from unsloth import FastLanguageModel21 22model, tokenizer = FastLanguageModel.from_pretrained(23    "Tuhin20/CodeLlama-7b-Instruct-FineTuned-JavaPython",24    load_in_4bit=True,25    device_map="auto",26)27 28prompt = "Write a Java function to reverse a linked list."29inputs = tokenizer(prompt, return_tensors="pt").to("cuda")30outputs = model.generate(**inputs, max_new_tokens=300)31print(tokenizer.decode(outputs[0], skip_special_tokens=True))32```33 34---35Trained and uploaded by **Tuhin20**36