Roger Wang 7a8987dac5

[Bugfix] Gracefully handle huggingface hub http error (#12571)

2025-01-31 08:19:35 +00:00

..

configs

Update pre-commit hooks (#12475)

2025-01-27 17:23:08 -07:00

processors

[Model] Port deepseek-vl2 processor, remove dependency (#12169)

2025-01-18 13:59:39 +08:00

tokenizer_group

[Bugfix] use right truncation for non-generative tasks (#12050)

2025-01-16 00:31:01 +08:00

tokenizers

[Bugfix] Mistral tokenizer encode accept list of str (#12149)

2025-01-17 16:47:53 +00:00

__init__.py

Fix the log to correct guide user to install modelscope (#9793)

2024-10-29 10:36:59 -07:00

config.py

[Bugfix] Gracefully handle huggingface hub http error (#12571)

2025-01-31 08:19:35 +00:00

detokenizer_utils.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

detokenizer.py

[Bugfix] fix detokenizer shallow copy (#5919)

2024-10-22 15:38:12 -07:00

processor.py

[VLM] Support caching in merged multi-modal processor (#11396)

2024-12-27 17:22:48 +00:00

s3_utils.py

[Bugfix] Path join when building local path for S3 clone (#12353)

2025-01-24 11:06:07 +08:00

tokenizer.py

[VLM] Avoid unnecessary tokenization (#12310)

2025-01-22 11:08:31 +00:00

utils.py

[Core] Loading model from S3 using RunAI Model Streamer as optional loader (#10192)

2024-12-20 16:46:24 +00:00