Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
VPTQ-community
's Collections
VPTQ Llama 3.3 70B Instruct without finetune
VPTQ Llama 3.1 Nemotron 70B Instruct HF without finetune
VPTQ Llama 3.1 405B Instruct without finetune
VPTQ Mistral Large Instruct 2407 without finetune
VPTQ Llama 3.1 70B Instruct without finetune
VPTQ Qwen 2.5 72B Instruct without finetune
VPTQ Qwen 2.5 32B Instruct without finetune
VPTQ Qwen 2.5 14B Instruct without finetune
VPTQ Llama 3.1 8B Instruct without finetune
VPTQ Qwen 2.5 7B Instruct without finetune
Hessian and InvHessian Checkpoints
Reproduced VPTQ Tech Report Baseline
VPTQ Llama 3.1 8B Instruct without finetune
updated
Oct 18
arxiv.org/abs/2409.17066, VPTQ Llama 3.1 8B Instruct without finetune
Upvote
-
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-65536-woft
Updated
Nov 18
•
201
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-4096-woft
Updated
Nov 18
•
15
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-256-woft
Updated
Nov 18
•
84
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v12-k65536-4096-woft
Updated
about 1 month ago
•
320
•
2
Upvote
-
Share collection
View history
Collection guide
Browse collections