gpjt/Meta-Llama-3-8B-openassistant-guanaco-llama2-format

This is a fine-tune of meta-llama/Meta-Llama-3-8B on the gpjt/openassistant-guanaco-llama2-format, which in turn is a version of timdettmers/openassistant-guanaco adjusted to use my best guess at the Llama 2 prompt format (see the dataset card for more info).

Sample code to use it:

import sys
import time

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline


prompt_template = """
<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>

{question} [/INST]
{response}
"""


def ask_question(model, tokenizer, question):
    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_new_tokens=2048)
    prompt = prompt_template.format(question=question, response="")
    tokens_in = len(tokenizer(prompt)["input_ids"])
    start = time.time()
    result = pipe(prompt)
    end = time.time()
    generated_text = result[0]['generated_text']
    tokens_out = len(tokenizer(generated_text)["input_ids"])
    print(generated_text)
    tokens_generated = tokens_out - tokens_in
    time_taken = end - start
    tokens_per_second = tokens_generated / time_taken
    print(f"{tokens_generated} tokens in {time_taken:.2f}s: {tokens_per_second:.2f} tokens/s)")



def test_model():
    model_name = "gpjt/Meta-Llama-3-8B-openassistant-guanaco-llama2-format"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cuda", torch_dtype=torch.bfloat16)

    question = input("You: ")
    ask_question(model, tokenizer, question)



if __name__ == "__main__":
    test_model()