Llama-2-7b-chat-finetune

Llama-2-7b-chat-finetune

This is a fine-tuned version of Llama-2-7b-chat for conversational tasks using the Hugging Face Transformers library.

Model Details

• Base model: LLaMA-2 7B
• Task: Conversational text generation
• Framework: Transformers (PyTorch)
• Dataset: Finsocial/identity

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

# Load tokenizer and model from Hugging Face
tokenizer = AutoTokenizer.from_pretrained("hello231/Llama-2-7b-chat-finetune")
model = AutoModelForCausalLM.from_pretrained("hello231/Llama-2-7b-chat-finetune")

# Optional: Use pipeline for easy inference
chat = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto")

# Prompt
prompt = "### Human: Who are you?\n### Assistant:"

# Generate response
response = chat(prompt, max_new_tokens=200, do_sample=True, temperature=0.7)[0]["generated_text"]

# Output
print(response)