cnfusion
/

Mellum-4b-sft-python-mlx-8Bit

Text Generation

Eval Results (legacy)

text-generation-inference

8-bit precision

Model card Files Files and versions

Mellum-4b-sft-python-mlx-8Bit

4.27 GB

1 contributor

History: 4 commits

cnfusion's picture

Upload tokenizer_config.json with huggingface_hub

d776366 verified 9 months ago

.gitattributes
1.52 kB

initial commit 9 months ago
model.safetensors
4.27 GB
xet

Upload model.safetensors with huggingface_hub 9 months ago
model.safetensors.index.json
49.1 kB

Upload model.safetensors.index.json with huggingface_hub 9 months ago
tokenizer_config.json
5.65 kB

Upload tokenizer_config.json with huggingface_hub 9 months ago