QwQbb
/

Hy-MT2-30B-A3B-MLX-4bit

multilingual-translation

4-bit precision

affine-quantization

Mixture of Experts

Model card Files Files and versions

Hy-MT2-30B-A3B-MLX-4bit

16.9 GB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

QwQbb's picture

Update README.md

1d00620 verified about 9 hours ago

.gitattributes

1.52 kB
initial commit about 10 hours ago
LICENSE.txt

17.4 kB
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
NOTICE

640 Bytes
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
README.md

8.79 kB
Update README.md about 9 hours ago
chat_template.jinja

11.3 kB
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
config.json

11.6 kB
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
conversion_info.json

1.73 kB
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
hy_v3.py

8.35 kB
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
model-00001-of-00004.safetensors

5.36 GB
xet

Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
model-00002-of-00004.safetensors

5.3 GB
xet

Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
model-00003-of-00004.safetensors

5.3 GB
xet

Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
model-00004-of-00004.safetensors

962 MB
xet

Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
model.safetensors.index.json

163 kB
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
tokenizer.json

9.53 MB
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago
tokenizer_config.json

371 Bytes
Upload Hy-MT2-30B-A3B MLX 4bit conversion about 9 hours ago