AlpinDale 6c43e00e60 add jamba modeling code vor 8 Monaten
..
gguf fcfb72af24 Support arbitrary model in GGUF. (#381) vor 9 Monaten
__init__.py 07aa2a492f upstream: add option to specify tokenizer vor 1 Jahr
block.py ac82b67f75 feat: naive context shift and various QoL changes (#289) vor 10 Monaten
config.py 6c43e00e60 add jamba modeling code vor 8 Monaten
grammar.py 0527131e93 fix: grammar logits processor (#268) vor 10 Monaten
logger.py f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) vor 9 Monaten
logits_processor.py 3df36ee07d fix: logit bias logitproc (#278) vor 10 Monaten
outputs.py c18bf116da fix stop strings not being excluded from outputs vor 9 Monaten
sampling_params.py c18bf116da fix stop strings not being excluded from outputs vor 9 Monaten
sequence.py c18bf116da fix stop strings not being excluded from outputs vor 9 Monaten
test_utils.py 50c2434267 move megatron to a top-level directory vor 9 Monaten
utils.py 531969a0b2 move merge_async_iterators to common utils vor 9 Monaten