| .. |
|
__init__.py
|
bd9279198c
refactor: rename init file and update app.py to enable parsing method
|
il y a 6 mois |
|
base_predictor.py
|
a3e2e7bd86
fix: adjust default top_p and top_k parameters for improved model performance
|
il y a 5 mois |
|
hf_predictor.py
|
a29489ef51
refactor: update config file name and enhance model path handling
|
il y a 5 mois |
|
predictor.py
|
76259a80ff
fix: update backend references from huggingface to transformers in client and predictor modules
|
il y a 5 mois |
|
sglang_client_predictor.py
|
8e55a52693
feat: add mineru-vlm backend.
|
il y a 6 mois |
|
sglang_engine_predictor.py
|
8e55a52693
feat: add mineru-vlm backend.
|
il y a 6 mois |
|
token_to_middle_json.py
|
3ff994c45e
refactor: close PDF document after processing to improve resource management
|
il y a 5 mois |
|
utils.py
|
8e55a52693
feat: add mineru-vlm backend.
|
il y a 6 mois |
|
vlm_analyze.py
|
8737ebb2e2
feat: remove model path parameter from vlm_doc_analyze and streamline model loading
|
il y a 5 mois |
|
vlm_magic_model.py
|
4f6d8d7ca5
fix: improve LaTeX delimiter handling by replacing valid and invalid pairs
|
il y a 5 mois |
|
vlm_middle_json_mkcontent.py
|
4eaa85fd31
refactor: update make mode constants to improve content list handling
|
il y a 5 mois |
myhloli
8737ebb2e2
feat: remove model path parameter from vlm_doc_analyze and streamline model loading