Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
tiiuae
/
Falcon3-7B-Instruct-1.58bit
like
15
Follow
Technology Innovation Institute
1.66k
Text Generation
Transformers
Safetensors
llama
bitnet
falcon3
conversational
text-generation-inference
8-bit precision
arxiv:
2402.17764
License:
falcon-llm-license
Model card
Files
Files and versions
xet
Community
1
Train
Deploy
Use this model
main
Falcon3-7B-Instruct-1.58bit
3.28 GB
2 contributors
History:
5 commits
ybelkada
(fix): align quantized models tokenizers with un-quantized ones (
#1
)
84526f3
verified
10 months ago
.gitattributes
Safe
1.52 kB
falcon3 release
11 months ago
README.md
Safe
4.13 kB
Update README.md
10 months ago
config.json
Safe
909 Bytes
falcon3 release
11 months ago
generation_config.json
Safe
118 Bytes
falcon3 release
11 months ago
model.safetensors
3.27 GB
xet
falcon3 release
11 months ago
special_tokens_map.json
Safe
826 Bytes
Upload tokenizer
11 months ago
tokenizer.json
Safe
9.78 MB
Upload tokenizer
11 months ago
tokenizer_config.json
Safe
365 kB
(fix): align quantized models tokenizers with un-quantized ones (#1)
10 months ago
