wesjos/SFT-llama3-8b-alpaca

LLaMA3-8B-Instruct SFT on Alpaca Dataset

This model is fine-tuned from LLaMA3.1-8B-Instruct using Supervised Fine-Tuning (SFT) on the "FreedomIntelligence/alpaca-gpt4-chinese" dataset.
The fine-tuning process aims to enhance the model's instruction-following and conversational alignment capabilities.

---

🧠 Training Information

• Base Model: LLaMA3-8B-Instruct
• Dataset: Stanford Alpaca
• Training Type: Supervised Fine-Tuning (SFT)
• Framework: PyTorch + Hugging Face Transformers

---

💻 Usage Example

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = 'wesjos/SFT-llama3-8b-alpaca'

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="bfloat16")

alpaca_prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{}

### Response:
"""

inputs = tokenizer(
[
    alpaca_prompt.format(
        "请你介绍一下自己",
    )
], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=1024, use_cache=True,temperature=0.9,do_sample=True,top_p=0.95,top_k=20)
print(tokenizer.batch_decode(outputs)[0])