Llama-2-QLoRA

Aquí se muestra cómo usarlo con textos en HuggingFace:

import torch
import transformers
from transformers import LlamaTokenizer, LlamaForCausalLM
tokenizer = LlamaTokenizer.from_pretrained("uf-aice-lab/Llama-2-QLoRA")
model = LlamaForCausalLM.from_pretrained(
"uf-aice-lab/Llama-2-QLoRA",
load_in_8bit=False,
torch_dtype=torch.float16,
device_map="auto",
)
def generate_prompt(instruction, input=None):
    if input:
        return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
        ### Instruction:
        {instruction}
        ### Input:
        {input}
        ### Response:"""
    else:
        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
        ### Instruction:
        {instruction}
        ### Response:"""

def evaluate(
    instruction,
    input=None,
    temperature=0.1,
    top_p=0.75,
    top_k=40,
    num_beams=4,
    max_new_tokens=128,
    **kwargs,
):
    prompt = generate_prompt(instruction, input)
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].to(device)
    generation_config = GenerationConfig(
        temperature=temperature,
        top_p=top_p,
        top_k=top_k,
        num_beams=num_beams,
        **kwargs,
    )
    with torch.no_grad():
        generation_output = model.generate(
            input_ids=input_ids,
            generation_config=generation_config,
            return_dict_in_generate=True,
            output_scores=True,
            max_new_tokens=max_new_tokens,
        )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.split("### Response:")[1].strip()

instruction = 'write your instruction here'
inputs = 'write your inputs here'
output= evaluate(instruction, input=inputs, temperature=0.1, top_p=0.75, top_k=40, num_beams=4, max_new_tokens=128,)