This revision is from 2024/07/16 20:52. You can Restore it.

The .gguf format is typically used with the llama.cpp project and its Python bindings, not with the Hugging Face Transformers library. To use a .gguf file, you need to use a different library, such as llama-cpp-python.

python3 -m pip install --upgrade pip
pip install transformers
pip install torch
pip install llama-cpp-python
Copy

Python script:

import os
from llama_cpp import Llama

model_path = "/home/x/Downloads/Lexi-Llama-3-8B-Uncensored_Q8_0.gguf"

# Load the model
llm = Llama(model_path=model_path)

# Initialize conversation history
conversation = []

print("Welcome! Type 'exit' to end the conversation.")

while True:
    # Get user input
    user_input = input("You: ").strip()
    
    # Check if user wants to exit
    if user_input.lower() == 'exit':
        print("Goodbye!")
        break
    
    # Add user input to conversation history
    conversation.append(f"Human: {user_input}")
    
    # Construct the prompt with conversation history
    prompt = "\n".join(conversation) + "\nAI:"
    
    # Generate a response
    response = llm(prompt, max_tokens=200, stop=["Human:", "\n"])
    
    # Extract and print the response
    ai_response = response['choices'][0]['text'].strip()
    print("AI:", ai_response)
    
    # Add AI response to conversation history
    conversation.append(f"AI: {ai_response}")Copy

Execute:

python llm_script.py
Copy

To load a hugging face transformer model directly...

import torch

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "internlm/internlm2-chat-7b"  # This is the Hugging Face model ID
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Move model to GPU if available
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)

# Initialize conversation history
conversation = []

print("Welcome! Type 'exit' to end the conversation.")

while True:
    # Get user input
    user_input = input("You: ").strip()
    
    # Check if user wants to exit
    if user_input.lower() == 'exit':
        print("Goodbye!")
        break
    
    # Add user input to conversation history
    conversation.append(f"Human: {user_input}")
    
    # Construct the prompt with conversation history
    prompt = "\n".join(conversation) + "\nAI:"
    
    # Tokenize input
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    
    # Generate response
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=200,
            num_return_sequences=1,
            do_sample=True,
            temperature=0.7,
            top_p=0.95,
            no_repeat_ngram_size=3,
            pad_token_id=tokenizer.eos_token_id
        )
    
    # Decode and print the response
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    ai_response = response[len(prompt):].strip()
    print("AI:", ai_response)
    
    # Add AI response to conversation history
    conversation.append(f"AI: {ai_response}")
Copy