Downloads · 30 days
13
31% of all-time downloads
Legion-V2.1-LLaMa-70B-FP8-Dynamic
tmfi-us/Legion-V2.1-LLaMa-70B-FP8-Dynamic
Legion-V2.1-LLaMa-70B-FP8-Dynamic is a machine learning model from tmfi-us. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.3.
FP8 w8a8 dynamic quants of Tarek07/Legion-V2.1-LLaMa-70B.
All-time downloads
42
Public
Parameters
70.6B
72.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors72.7 GB · 100%
Parameter types
How the weights are stored.
F8_E4M368.5B · 97%
Base models
Model card
From the Hugging Face model README
About
FP8 w8a8 dynamic quants of Tarek07/Legion-V2.1-LLaMa-70B.
Used following Python script with llmcompressor to generate:
from transformers import AutoTokenizer, AutoModelForCausalLM
from llmcompressor.transformers import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
MODEL_ID = 'Tarek07/Legion-V2.1-LLaMa-70B'
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID, device_map="auto", torch_dtype="auto",
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
# Configure the simple PTQ quantization
recipe = QuantizationModifier(
targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"])
# Apply the quantization algorithm.
oneshot(model=model, recipe=recipe)
# Save the model.
SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
model.save_pretrained(SAVE_DIR)
tokenizer.save_pretrained(SAVE_DIR)
Quantization recipe can be found in recipe.yaml
- Type
- llama
- License
- llama3.3
- Created
- Mar 30, 2025
- Updated
- Mar 30, 2025