使用python调用llama3进行对话的操作步骤

pip3 install transformers torch

pip3 install -U huggingface_hub
pip install -U "huggingface_hub[cli]"

export HF_ENDPOINT=https://hf-mirror.com

huggingface-cli download meta-llama/Meta-Llama-3-8B  --local-dir Meta-Llama-3-8B

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "meta-llama/Meta-Llama-3-8B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

import transformers
import torch

model_id = "meta-llama/Meta-Llama-3-8B"
pipeline = transformers.pipeline(
    "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
pipeline("Hey how are you doing today?")