 AlpinDale
|
4599c98f99
feat: dynamic image size support for VLMs
|
7 months ago |
 AlpinDale
|
0f4a9ee77b
quantized lm_head (#582)
|
7 months ago |
|
AlpinDale
|
ae04f57ec1
feat: Pipeline Parallel support (#581)
|
7 months ago |
|
AlpinDale
|
3a0fdf7b9b
chore: remove `image_input_type` from VLM config
|
7 months ago |
|
AlpinDale
|
4cdc810b1c
fix: minor TP issues with vision models
|
7 months ago |
|
AlpinDale
|
b6ff0623a6
chore: clean up branding
|
7 months ago |
|
AlpinDale
|
c0c336aaa3
refactor: registry for processing model inputs; quick_gelu; clip model support
|
7 months ago |
|
AlpinDale
|
c5d8028668
fix: no need to redefine supports_vision and supports_lora in model class
|
7 months ago |
|
AlpinDale
|
56e0b8223c
chore: add base class for LoRA-supported models
|
7 months ago |
|
AlpinDale
|
190276865a
feat: llava-next support
|
7 months ago |
