Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
slowfastai
/
Moonlight-16B-A3B-bnb-4bit
like
1
Follow
SlowFast AI
1
Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
text-generation-inference
4-bit precision
bitsandbytes
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Moonlight-16B-A3B-bnb-4bit
9.25 GB
1 contributor
History:
9 commits
basicv8vc
Update README.md
caecee0
verified
10 months ago
.gitattributes
1.52 kB
initial commit
11 months ago
README.md
1.34 kB
Update README.md
10 months ago
config.json
2.05 kB
update repo name
11 months ago
configuration_deepseek.py
10.7 kB
Upload 3 files
11 months ago
generation_config.json
97 Bytes
Upload DeepseekV3ForCausalLM
11 months ago
model-00001-of-00002.safetensors
5 GB
xet
Upload DeepseekV3ForCausalLM
11 months ago
model-00002-of-00002.safetensors
4.24 GB
xet
Upload DeepseekV3ForCausalLM
11 months ago
model.safetensors.index.json
3.21 MB
Upload DeepseekV3ForCausalLM
11 months ago
modeling_deepseek.py
75.9 kB
Upload 3 files
11 months ago
special_tokens_map.json
695 Bytes
Upload tokenizer
11 months ago
tiktoken.model
2.8 MB
xet
Upload tokenizer
11 months ago
tokenization_moonshot.py
11.1 kB
Upload 3 files
11 months ago
tokenizer_config.json
2.69 kB
Upload tokenizer
11 months ago
