AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-01 01:26:03 -04:00
Code Issues Packages Projects Releases Wiki Activity

Support LLaVA v1.5 7B (#4348)

Browse Source
This commit is contained in:
Jiashu Xu 2023-10-22 11:49:04 -04:00 committed by GitHub
parent 05741821a5
commit c544f5cc51
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 22 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
extensions/multimodal/README.md
View File

@ -13,7 +13,10 @@ https://user-images.githubusercontent.com/3718215/233817203-69b57e77-0c55-4fd6-b
To run this extension, download a LLM that supports multimodality, and then start server.py with the appropriate `--multimodal-pipeline` argument. Examples:
```
# LLaVA 1.5 13B has the best performance
python server.py --model liuhaotian_llava-v1.5-13b --multimodal-pipeline llava-v1.5-13b --load-in-4bit
# LLaVA 1.5 7B is relatively weaker, but requires less memory
python server.py --model liuhaotian_llava-v1.5-7b --multimodal-pipeline llava-v1.5-7b --load-in-4bit
python server.py --model TheBloke_llava-v1.5-13B-GPTQ_gptq-4bit-32g-actorder_True --multimodal-pipeline llava-v1.5-13b --disable_exllama --loader autogptq
python server.py --model wojtab_llava-7b-v0-4bit-128g --multimodal-pipeline llava-7b
python server.py --model wojtab_llava-13b-v0-4bit-128g --multimodal-pipeline llava-13b

12
extensions/multimodal/pipelines/llava/llava.py
View File

@ -248,3 +248,15 @@ class LLaVA_v1_5_13B_Pipeline(LLaVA_v0_13B_Pipeline):
@staticmethod
def placeholder_embeddings() -> torch.Tensor:
return LLaVA_v0_Pipeline.embed_tokens(encode("<unk>"*576, add_bos_token=False)[0])
class LLaVA_v1_5_7B_Pipeline(LLaVA_v1_5_13B_Pipeline):
@staticmethod
def name() -> str:
return "llava-v1.5-7b"
@staticmethod
def llava_projector_shape() -> Tuple[int, int]:
return (1024, 4096, 4096)
@staticmethod
def llava_projector_repo() -> str:
return "liuhaotian/llava-v1.5-7b"

8
extensions/multimodal/pipelines/llava/pipelines.py
View File

@ -2,7 +2,7 @@ from typing import Optional
from extensions.multimodal.abstract_pipeline import AbstractMultimodalPipeline
available_pipelines = ['llava-7b', 'llava-13b', 'llava-llama-2-13b', 'llava-v1.5-13b']
available_pipelines = ['llava-7b', 'llava-13b', 'llava-llama-2-13b', 'llava-v1.5-13b', 'llava-v1.5-7b']
def get_pipeline(name: str, params: dict) -> Optional[AbstractMultimodalPipeline]:
@ -15,6 +15,9 @@ def get_pipeline(name: str, params: dict) -> Optional[AbstractMultimodalPipeline
if name == 'llava-llama-2-13b':
from .llava import LLaVA_LLaMA_2_13B_Pipeline
return LLaVA_LLaMA_2_13B_Pipeline(params)
if name == 'llava-v1.5-7b':
from .llava import LLaVA_v1_5_7B_Pipeline
return LLaVA_v1_5_7B_Pipeline(params)
if name == 'llava-v1.5-13b':
from .llava import LLaVA_v1_5_13B_Pipeline
return LLaVA_v1_5_13B_Pipeline(params)
@ -32,6 +35,9 @@ def get_pipeline_from_model_name(model_name: str, params: dict) -> Optional[Abst
if '13b' in model_name.lower():
from .llava import LLaVA_v1_5_13B_Pipeline
return LLaVA_v1_5_13B_Pipeline(params)
if '7b' in model_name.lower():
from .llava import LLaVA_v1_5_7B_Pipeline
return LLaVA_v1_5_7B_Pipeline(params)
else:
if '7b' in model_name.lower():
from .llava import LLaVA_v0_7B_Pipeline