Mininglamp-2718
/

Mano-P

Image-Text-to-Text

desktop-automation

Model card Files Files and versions

Mano-P / w8a16

5.12 GB

Ctrl+K

Ctrl+K

4 contributors

History: 3 commits

hhhhhalf's picture

Update w8a16 model to ckpt124146 (Qwen3-VL 4B thinking, MLX 8-bit)

54c435d verified 6 days ago

README.md

84 Bytes
Update w8a16 model to ckpt124146 (Qwen3-VL 4B thinking, MLX 8-bit) 6 days ago
added_tokens.json

707 Bytes
Rename original/ → w8a16/ about 1 month ago
args.json

21.3 kB
Rename original/ → w8a16/ about 1 month ago
chat_template.jinja

5.2 kB
Update w8a16 model to ckpt124146 (Qwen3-VL 4B thinking, MLX 8-bit) 6 days ago
config.json

2.15 kB
Rename original/ → w8a16/ about 1 month ago
generation_config.json

192 Bytes
Update w8a16 model to ckpt124146 (Qwen3-VL 4B thinking, MLX 8-bit) 6 days ago
model.safetensors

5.1 GB
xet

Update w8a16 model to ckpt124146 (Qwen3-VL 4B thinking, MLX 8-bit) 6 days ago
model.safetensors.index.json

100 kB
Rename original/ → w8a16/ about 1 month ago
preprocessor_config.json

390 Bytes
Rename original/ → w8a16/ about 1 month ago
processor_config.json

1.26 kB
Rename original/ → w8a16/ about 1 month ago
special_tokens_map.json

613 Bytes
Rename original/ → w8a16/ about 1 month ago
tokenizer.json

11.4 MB
xet

Rename original/ → w8a16/ about 1 month ago
tokenizer_config.json

389 Bytes
Rename original/ → w8a16/ about 1 month ago
video_preprocessor_config.json

817 Bytes
Rename original/ → w8a16/ about 1 month ago
vocab.json

2.78 MB
Rename original/ → w8a16/ about 1 month ago
zero_to_fp32.py

33.3 kB
Update w8a16 model to ckpt124146 (Qwen3-VL 4B thinking, MLX 8-bit) 6 days ago