mlx-community
/

Kimi-VL-A3B-Thinking-4bit

Image-Text-to-Text

feature-extraction

Model card Files Files and versions

Kimi-VL-A3B-Thinking-4bit

9.85 GB

Ctrl+K

Ctrl+K

2 contributors

History: 23 commits

prince-canuma's picture

Upload tokenizer_config.json with huggingface_hub

c4f541b verified 2 months ago

.gitattributes

1.57 kB
Add pre-converted tokenizer.json (no tiktoken dependency) 2 months ago
README.md

886 Bytes
Upload folder using huggingface_hub 12 months ago
chat_template.jinja

1.03 kB
Upload folder using huggingface_hub 12 months ago
config.json

6.81 kB
Add <|im_assistant|> to eos_token_id: [163584, 163586] 2 months ago
configuration_kimi_vl.py

13.2 kB
Add files using upload-large-folder tool 12 months ago
image_processing_kimi_vl.py

4.68 kB
Add files using upload-large-folder tool 12 months ago
model-00001-of-00002.safetensors

5.36 GB
xet

Upload folder using huggingface_hub 12 months ago
model-00002-of-00002.safetensors

4.48 GB
xet

Upload folder using huggingface_hub 12 months ago
model.safetensors.index.json

588 kB
Upload folder using huggingface_hub 12 months ago
preprocessor_config.json

483 Bytes
Upload folder using huggingface_hub 12 months ago
processing_kimi_vl.py

7.71 kB
Add files using upload-large-folder tool 12 months ago
processor_config.json

122 Bytes
Upload folder using huggingface_hub 12 months ago
special_tokens_map.json

785 Bytes
Add files using upload-large-folder tool 12 months ago
tokenizer.json

19.5 MB
xet

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

449 Bytes
Upload tokenizer_config.json with huggingface_hub 2 months ago