| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 rok pred |
|
block.py
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
1 rok pred |
|
config.py
|
76d6f49bbb
fix: modelscope downloads
|
7 mesiacov pred |
|
grammar.py
|
0527131e93
fix: grammar logits processor (#268)
|
1 rok pred |
|
inputs.py
|
9d19811d4f
avoid the nee dto pass `None` values to `Sequence.inputs`
|
7 mesiacov pred |
|
logger.py
|
46159b107a
formatting: pt1
|
8 mesiacov pred |
|
logits_processor.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 mesiacov pred |
|
outputs.py
|
90ceab32ff
refactor: consolidate prompt args to LLM engines
|
7 mesiacov pred |
|
pooling_params.py
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
7 mesiacov pred |
|
sampling_params.py
|
e8b7f53321
allow prompt token IDs in the logits processor api
|
7 mesiacov pred |
|
sequence.py
|
8d77c69cbd
feat: support image processor and add llava example
|
7 mesiacov pred |
|
test_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 mesiacov pred |
|
utils.py
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 mesiacov pred |
AlpinDale
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)