Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
cybermotaz
/
Falcon-H1R-7B-NVFP4
like
0
Text Generation
Transformers
Safetensors
falcon_h1
nvidia
nvfp4
quantized
blackwell
4-bit precision
falcon
mamba
hybrid
vllm
optimized
conversational
8-bit precision
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Falcon-H1R-7B-NVFP4
5.43 GB
1 contributor
History:
4 commits
cybermotaz
Remove ASCII art, keep emojis 🦌🦅
e5c2066
verified
3 days ago
.gitattributes
1.57 kB
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
README.md
7.96 kB
Remove ASCII art, keep emojis 🦌🦅
3 days ago
chat_template.jinja
4.24 kB
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
config.json
2.16 kB
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
generation_config.json
152 Bytes
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
hf_quant_config.json
268 Bytes
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
model-00001-of-00002.safetensors
4.62 GB
xet
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
model-00002-of-00002.safetensors
799 MB
xet
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
model.safetensors.index.json
132 kB
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
special_tokens_map.json
18.9 kB
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
tokenizer.json
10.5 MB
xet
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
tokenizer_config.json
202 kB
Initial upload: Falcon H1R 7B NVFP4 - 2x faster, 3x smaller, <1% accuracy loss
3 days ago
