ChatHuggingFace 集成

import getpass
import os

if not os.getenv("HUGGINGFACEHUB_API_TOKEN"):
    os.environ["HUGGINGFACEHUB_API_TOKEN"] = getpass.getpass("Enter your token: ")

import getpass
import os

os.environ["HUGGINGFACEHUB_API_TOKEN"] = getpass.getpass(
    "Enter your Hugging Face API key: "
)

pip install -qU  langchain-huggingface text-generation transformers google-search-results numexpr langchainhub sentencepiece jinja2 bitsandbytes accelerate

from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint

llm = HuggingFaceEndpoint(
    repo_id="deepseek-ai/DeepSeek-R1-0528",
    task="text-generation",
    max_new_tokens=512,
    do_sample=False,
    repetition_penalty=1.03,
    provider="auto",  # 让 Hugging Face 为您选择最佳提供商
)

chat_model = ChatHuggingFace(llm=llm)

The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.
Token is valid (permission: fineGrained).
Your token has been saved to /Users/isaachershenson/.cache/huggingface/token
Login successful

llm = HuggingFaceEndpoint(
    repo_id="deepseek-ai/DeepSeek-R1-0528",
    task="text-generation",
    provider="hyperbolic",  # 在此处设置您的提供商
    # provider="nebius",
    # provider="together",
)

chat_model = ChatHuggingFace(llm=llm)

from langchain_huggingface import ChatHuggingFace, HuggingFacePipeline

llm = HuggingFacePipeline.from_model_id(
    model_id="HuggingFaceH4/zephyr-7b-beta",
    task="text-generation",
    pipeline_kwargs=dict(
        max_new_tokens=512,
        do_sample=False,
        repetition_penalty=1.03,
    ),
)

chat_model = ChatHuggingFace(llm=llm)

config.json:   0%|          | 0.00/638 [00:00<?, ?B/s]

model.safetensors.index.json:   0%|          | 0.00/23.9k [00:00<?, ?B/s]

Downloading shards:   0%|          | 0/8 [00:00<?, ?it/s]

model-00001-of-00008.safetensors:   0%|          | 0.00/1.89G [00:00<?, ?B/s]

model-00002-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]

model-00003-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]

model-00004-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]

model-00005-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]

model-00006-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]

model-00007-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]

model-00008-of-00008.safetensors:   0%|          | 0.00/816M [00:00<?, ?B/s]

Loading checkpoint shards:   0%|          | 0/8 [00:00<?, ?it/s]

generation_config.json:   0%|          | 0.00/111 [00:00<?, ?B/s]

from transformers import BitsAndBytesConfig

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype="float16",
    bnb_4bit_use_double_quant=True,
)

llm = HuggingFacePipeline.from_model_id(
    model_id="HuggingFaceH4/zephyr-7b-beta",
    task="text-generation",
    pipeline_kwargs=dict(
        max_new_tokens=512,
        do_sample=False,
        repetition_penalty=1.03,
        return_full_text=False,
    ),
    model_kwargs={"quantization_config": quantization_config},
)

chat_model = ChatHuggingFace(llm=llm)

from langchain.messages import (
    HumanMessage,
    SystemMessage,
)

messages = [
    SystemMessage(content="You're a helpful assistant"),
    HumanMessage(
        content="What happens when an unstoppable force meets an immovable object?"
    ),
]

ai_msg = chat_model.invoke(messages)

print(ai_msg.content)

According to the popular phrase and hypothetical scenario, when an unstoppable force meets an immovable object, a paradoxical situation arises as both forces are seemingly contradictory. On one hand, an unstoppable force is an entity that cannot be stopped or prevented from moving forward, while on the other hand, an immovable object is something that cannot be moved or displaced from its position.

In this scenario, it is un