model_path = "mistralai/Mistral-7B-Instruct-v0.1"
bnb_config = BitsAndBytesConfig(
    load_in_8bit=True
)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, quantization_config=bnb_config, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_path)

Load in pipeline

python

text_generation_pipeline = transformers.pipeline(
    model=model,
    tokenizer=tokenizer,
    task="text-generation",
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.eos_token_id,
    repetition_penalty=1.1,
    return_full_text=True,
    max_new_tokens=100,
)
mistral_llm = HuggingFacePipeline(pipeline=text_generation_pipeline)

text = "what is mistral?"
mistral_llm.invoke(text)

dmitrybright/Mistral-7B-Instruct-v0.1-8bit

Mistral-7B-Instruct-v0.1-8bit

dmitrybright/
Mistral-7B-Instruct-v0.1-8bit