mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ
Image Classification
•
Updated
•
12
•
5
AI & ML interests
Computer Vision, LLMs, Multimodal Models, Model Compression
mobicham
updated
a
model
6 months ago
mobicham
updated
a
collection
7 months ago
🙋🏻♂️ gemlite hqq quant version "unlearns" tool calling (?)
4
#2 opened 7 months ago
by
Tonic
appoose
updated
a
model
7 months ago
appoose
published
a
model
7 months ago
mobicham
updated
a
collection
8 months ago
mobicham
published
2
models
8 months ago
mobicham
updated
a
model
8 months ago
Post
2129
Releasing HQQ Llama-3.1-70b 4-bit quantized version! Check it out at https://huggingface.co/mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq.
Achieves 99% of the base model performance across various benchmarks! Details in the model card.
Achieves 99% of the base model performance across various benchmarks! Details in the model card.
Post
1805
Excited to announce the release of our high-quality Llama-3.1 8B 4-bit HQQ/calibrated quantized model! Achieving an impressive 99.3% relative performance to FP16, it also delivers the fastest inference speed for transformers.
https://huggingface.co/mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib
https://huggingface.co/mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib
- 1 reply
Jilt
updated
a
dataset
almost 2 years ago
appoose
updated
a
Space
almost 2 years ago
mobicham
updated
3
models
almost 2 years ago