Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mit-han-lab
/
VILA1.5-13B-QServe-W8A8
like
1
Follow
MIT HAN Lab
82
Text Generation
Transformers
Safetensors
llava_llama
VILA
VLM
Inference Endpoints
arxiv:
2312.07533
arxiv:
2405.04532
License:
cc-by-nc-4.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
VILA1.5-13B-QServe-W8A8
/
llm
1 contributor
History:
1 commit
kentang1998
[Major] Add QServe-W8A8 version of VILA1.5 13B
d6bce15
3 months ago
config.json
Safe
852 Bytes
[Major] Add QServe-W8A8 version of VILA1.5 13B
3 months ago
generation_config.json
Safe
213 Bytes
[Major] Add QServe-W8A8 version of VILA1.5 13B
3 months ago
model.safetensors.index.json
Safe
29.9 kB
[Major] Add QServe-W8A8 version of VILA1.5 13B
3 months ago
pytorch_model.bin
Safe
13.4 GB
LFS
[Major] Add QServe-W8A8 version of VILA1.5 13B
3 months ago
special_tokens_map.json
Safe
438 Bytes
[Major] Add QServe-W8A8 version of VILA1.5 13B
3 months ago
tokenizer.model
Safe
500 kB
LFS
[Major] Add QServe-W8A8 version of VILA1.5 13B
3 months ago
tokenizer_config.json
Safe
964 Bytes
[Major] Add QServe-W8A8 version of VILA1.5 13B
3 months ago
