Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ronantakizawa
/
molmoact-7b-d-awq
like
1
Image-Text-to-Text
Transformers
Safetensors
English
molmoact
feature-extraction
awq
quantized
4-bit precision
vision-language
robotics
molmo
qwen2.5
siglip
llm-compressor
conversational
custom_code
compressed-tensors
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
molmoact-7b-d-awq
/
generation_config.json
ronantakizawa
Upload AWQ 4-bit quantized MolmoAct-7B-D (~6.1GB, 56.3% reduction)
e95ac0c
verified
about 2 months ago
raw
Copy download link
history
blame
contribute
delete
117 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
151643
,
"pad_token_id"
:
151643
,
"transformers_version"
:
"4.57.1"
}