BlueMoonlight
/

deepseek-moe-16b-chat-mlx-4Bit

4-bit precision

Model card Files Files and versions

deepseek-moe-16b-chat-mlx-4Bit

1 contributor

History: 13 commits

BlueMoonlight's picture

Upload README.md with huggingface_hub

9522677 verified about 2 months ago

.gitattributes

1.52 kB

initial commit about 2 months ago
README.md

1.03 kB

Upload README.md with huggingface_hub about 2 months ago
chat_template.jinja

459 Bytes

Upload chat_template.jinja with huggingface_hub about 2 months ago
config.json

1.41 kB

Upload config.json with huggingface_hub about 2 months ago
configuration_deepseek.py

10.2 kB

Upload configuration_deepseek.py with huggingface_hub about 2 months ago
generation_config.json

121 Bytes

Upload generation_config.json with huggingface_hub about 2 months ago
model-00001-of-00002.safetensors

5.35 GB
xet

Upload model-00001-of-00002.safetensors with huggingface_hub about 2 months ago
model-00002-of-00002.safetensors

3.87 GB
xet

Upload model-00002-of-00002.safetensors with huggingface_hub about 2 months ago
model.safetensors.index.json

84.3 kB

Upload model.safetensors.index.json with huggingface_hub about 2 months ago
modeling_deepseek.py

72.7 kB

Upload modeling_deepseek.py with huggingface_hub about 2 months ago
special_tokens_map.json

482 Bytes

Upload special_tokens_map.json with huggingface_hub about 2 months ago
tokenizer.json

7.5 MB

Upload tokenizer.json with huggingface_hub about 2 months ago
tokenizer_config.json

3.08 kB

Upload tokenizer_config.json with huggingface_hub about 2 months ago