fiveflow's picture
Update README.md
65fdc2d verified
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model-index:
  - name: fiveflow/KoLlama-3-8B-Instruct
    results: []
language:
  - ko

How to use

from transformers import AutoModelForCausalLM, AutoTokenizer, TextGenerationPipeline
model_path = 'fiveflow/KoLlama-3-8B-Instruct'
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, 
                                                  device_map="auto",
                                                #   load_in_4bit=True,
                                                  low_cpu_mem_usage=True)

pipe = TextGenerationPipeline(model = model, tokenizer = tokenizer)