metadata
language:
- en
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: llama3
new_version: meta-llama/Llama-3.1-8B-Instruct
Model quantized to FP8 using llm_compressor
from transformers import AutoTokenizer, AutoModelForCausalLM
from llmcompressor.transformers import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
# Define the model ID for the model you want to quantize
MODEL_ID = "meta-llama/Llama-3.1-8B-Instruct"
# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID, device_map="auto", torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
# Configure the quantization recipe
recipe = QuantizationModifier(targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"])
# Apply the quantization algorithm
oneshot(model=model, recipe=recipe)
# Define the directory to save the quantized model
SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
# Save the quantized model and tokenizer
model.save_pretrained(SAVE_DIR)
tokenizer.save_pretrained(SAVE_DIR)
print(f"Quantized model saved to (SAVE_DIR)")