TheBloke

/

Llama-2-7B-Chat-GPTQ

like 261

When I'm running the model it prints the next warning:" This is a friendly reminder - the current text generation call will exceed the model's predefined maximum length (4096). Depending on the model, you may observe exceptions, performance degradation, or nothing at all"
and the result that I get is garbage :" • • • • • • • \n \n• • • • • ................ • ◄ • Ü • • • ... "
How to Address and Improve Results?
This is my code:

import torch
from langchain import HuggingFacePipeline
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, pipeline
from auto_gptq import AutoGPTQForCausalLM
MODEL_NAME = "TheBloke/Llama-2-7b-Chat-GPTQ"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=True)

model = AutoGPTQForCausalLM.from_quantized(
    MODEL_NAME, torch_dtype=torch.float16, trust_remote_code=True, device_map="auto"
)

generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
generation_config.max_new_tokens = 1024
generation_config.temperature = 0.0001
generation_config.top_p = 0.95
generation_config.do_sample = True
generation_config.repetition_penalty = 1.15

text_pipeline = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    return_full_text=True,
    generation_config=generation_config,
)

llm = HuggingFacePipeline(pipeline=text_pipeline, model_kwargs={"temperature": 0})