Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mlx-community
/
Moonlight-16B-A3B-Instruct-4-bit
like
3
Follow
MLX Community
3.94k
Text Generation
Transformers
Safetensors
MLX
deepseek_v3
conversational
custom_code
4-bit precision
License:
mit
Model card
Files
Files and versions
Community
1
Train
Use this model
main
Moonlight-16B-A3B-Instruct-4-bit
1 contributor
History:
2 commits
awni
Add files using upload-large-folder tool
8503ff1
verified
6 days ago
.gitattributes
Safe
1.52 kB
initial commit
6 days ago
README.md
Safe
907 Bytes
Add files using upload-large-folder tool
6 days ago
config.json
Safe
1.64 kB
Add files using upload-large-folder tool
6 days ago
configuration_deepseek.py
10.7 kB
Add files using upload-large-folder tool
6 days ago
model-00001-of-00002.safetensors
Safe
5.28 GB
LFS
Add files using upload-large-folder tool
6 days ago
model-00002-of-00002.safetensors
Safe
3.7 GB
LFS
Add files using upload-large-folder tool
6 days ago
model.safetensors.index.json
Safe
87.5 kB
Add files using upload-large-folder tool
6 days ago
modeling_deepseek.py
75.9 kB
Add files using upload-large-folder tool
6 days ago
special_tokens_map.json
Safe
695 Bytes
Add files using upload-large-folder tool
6 days ago
tiktoken.model
2.8 MB
LFS
Add files using upload-large-folder tool
6 days ago
tokenization_moonshot.py
11.1 kB
Add files using upload-large-folder tool
6 days ago
tokenizer_config.json
Safe
2.66 kB
Add files using upload-large-folder tool
6 days ago
