Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
tiiuae
/
Falcon3-10B-Instruct-1.58bit
like
13
Follow
Technology Innovation Institute
1.18k
Text Generation
Transformers
Safetensors
llama
bitnet
falcon3
conversational
text-generation-inference
Inference Endpoints
8-bit precision
arxiv:
2402.17764
License:
falcon-llm-license
Model card
Files
Files and versions
Community
4
Train
Deploy
Use this model
main
Falcon3-10B-Instruct-1.58bit
3 contributors
History:
7 commits
ybelkada
(fix): align quantized models tokenizers with un-quantized ones (
#4
)
4b61e88
verified
23 days ago
.gitattributes
1.52 kB
falcon3 release
about 2 months ago
README.md
4.13 kB
Update README.md
about 2 months ago
config.json
840 Bytes
falcon3 release
about 2 months ago
generation_config.json
118 Bytes
falcon3 release
about 2 months ago
model.safetensors
3.99 GB
LFS
falcon3 release
about 2 months ago
special_tokens_map.json
826 Bytes
Upload tokenizer
about 2 months ago
tokenizer.json
9.78 MB
Upload tokenizer
about 2 months ago
tokenizer_config.json
365 kB
(fix): align quantized models tokenizers with un-quantized ones (#4)
23 days ago
