Downloads · 30 days
6
19% of all-time downloads
Llama-2-7b-hf-FP8-OC
hyper-accel/Llama-2-7b-hf-FP8-OC
Llama-2-7b-hf-FP8-OC is a machine learning model from hyper-accel. 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 apache-2.0.
Derived from unsloth/llama-2-7b at revision 93d41f48d9d232fd17620e20fc7d22b03cfdc83c.
All-time downloads
31
Public
Parameters
6.7B
7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7 GB · 100%
Parameter types
How the weights are stored.
I86.5B · 96%
Base models
Model card
From the Hugging Face model README
llama-2-7b FP8-OC
Derived from unsloth/llama-2-7b at revision 93d41f48d9d232fd17620e20fc7d22b03cfdc83c.
LLM Compressor quantizes attention and MLP matrix weights to E4M3FN with one FP32 scale per output channel. HART stores those FP8 bytes and scales in the Bertha EVT0 packed weight format. Other model parameters remain BF16. This checkpoint requires the HyperAccel vLLM plugin.
- Type
- llama
- License
- apache-2.0
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026