|
|
--- |
|
|
license: other |
|
|
license_name: nvidia-open-model-license |
|
|
license_link: >- |
|
|
https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ |
|
|
base_model: |
|
|
- nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 |
|
|
--- |
|
|
|
|
|
# Llama-3_3-Nemotron-Super-49B-v1_5-FP8-Dynamic |
|
|
|
|
|
FP8 quantization of https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 |
|
|
|
|
|
## Creation |
|
|
|
|
|
Created with llmcompressor using the following code: |
|
|
|
|
|
``` |
|
|
import sys |
|
|
|
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
from llmcompressor.transformers import oneshot |
|
|
from llmcompressor.modifiers.quantization import QuantizationModifier |
|
|
|
|
|
MODEL_ID = sys.argv[1] |
|
|
SAVE_DIR = sys.argv[2] |
|
|
|
|
|
# Load the model |
|
|
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto", local_files_only=True, trust_remote_code=True) |
|
|
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, local_files_only=True, trust_remote_code=True) |
|
|
|
|
|
# Configure the simple PTQ quantization |
|
|
recipe = QuantizationModifier(targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"]) |
|
|
|
|
|
# Apply the quantization algorithm. |
|
|
oneshot(model=model, recipe=recipe, trust_remote_code_model=True) |
|
|
|
|
|
# Save the model |
|
|
model.save_pretrained(SAVE_DIR) |
|
|
tokenizer.save_pretrained(SAVE_DIR) |
|
|
``` |
