| .. |
|
gguf
|
fcfb72af24
Support arbitrary model in GGUF. (#381)
|
hace 9 meses |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
hace 1 año |
|
block.py
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
hace 10 meses |
|
config.py
|
6c43e00e60
add jamba modeling code
|
hace 9 meses |
|
grammar.py
|
0527131e93
fix: grammar logits processor (#268)
|
hace 11 meses |
|
logger.py
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
hace 9 meses |
|
logits_processor.py
|
3df36ee07d
fix: logit bias logitproc (#278)
|
hace 10 meses |
|
outputs.py
|
c18bf116da
fix stop strings not being excluded from outputs
|
hace 9 meses |
|
sampling_params.py
|
c18bf116da
fix stop strings not being excluded from outputs
|
hace 9 meses |
|
sequence.py
|
c18bf116da
fix stop strings not being excluded from outputs
|
hace 9 meses |
|
test_utils.py
|
50c2434267
move megatron to a top-level directory
|
hace 9 meses |
|
utils.py
|
531969a0b2
move merge_async_iterators to common utils
|
hace 9 meses |
AlpinDale
6c43e00e60
add jamba modeling code