Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
donghyunli
/
Llama-2-7b-KronQ-W4A16
like
0
Text Generation
Safetensors
English
kronq
quantization
int4
weight-only
8-bit precision
arxiv:
2607.07964
License:
llama2
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
main
Llama-2-7b-KronQ-W4A16
3.78 GB
Ctrl+K
Ctrl+K
2 contributors
History:
10 commits
donghyunli
Update results table
25e16bc
verified
23 days ago
.gitattributes
1.52 kB
initial commit
about 2 months ago
README.md
1.92 kB
Update results table
23 days ago
kronq_packed_config.json
86 Bytes
Update checkpoint (H_G recomputed with sampled Fisher)
23 days ago
model.safetensors
3.78 GB
xet
Update checkpoint (H_G recomputed with sampled Fisher)
23 days ago
special_tokens_map.json
414 Bytes
KronQ W4A16 packed int4 (L2-7B)
about 2 months ago
tokenizer.json
1.84 MB
KronQ W4A16 packed int4 (L2-7B)
about 2 months ago
tokenizer.model
500 kB
xet
KronQ W4A16 packed int4 (L2-7B)
about 2 months ago
tokenizer_config.json
776 Bytes
KronQ W4A16 packed int4 (L2-7B)
about 2 months ago
