Artem Chumachenko
|
d6f4f80f3f
Fix Mixtral-related issues (#570)
|
1 rok temu |
Alexander Borzunov
|
a26559ff65
Fix `.generate(input_ids=...)` (#485)
|
2 lat temu |
Alexander Borzunov
|
de2475f31c
Make client compatible with transformers' GenerationMixin (#464)
|
2 lat temu |
Alexander Borzunov
|
8c546d988a
Test Llama, rebalancing, throughput eval, and all CLI scripts (#452)
|
2 lat temu |
justheuristic
|
5af04524dd
Split long sequences into chunks (#403)
|
2 lat temu |
Artem Chumachenko
|
b9f0a5467f
Support peft LoRA adapters (#335)
|
2 lat temu |
Alexander Borzunov
|
cb3f018f9f
Add LLaMA support (#323)
|
2 lat temu |
Max Ryabinin
|
793726b041
Speed up loading blocks using init with meta weights (#285)
|
2 lat temu |
Alexander Borzunov
|
fee19e9b9b
Use get_logger(__name__) instead of get_logger(__file__) (#265)
|
2 lat temu |
Alexander Borzunov
|
668b736031
Fix logging: do not duplicate lines, enable colors in Colab (#156)
|
2 lat temu |
Max Ryabinin
|
bd91be27ea
Add missing methods for SamplingAlgorithm, fix docstrings (#107)
|
2 lat temu |
justheuristic
|
b04982c1a2
Bump transformers to 4.25.1 (#151)
|
2 lat temu |
Alexander Borzunov
|
7bd5916744
Make Petals a pip-installable package (attempt 2) (#102)
|
2 lat temu |
Artem Chumachenko
|
fdb3583a8c
Add Beam Search decoding algorithm (#87)
|
2 lat temu |
justheuristic
|
d271b75dd4
Let users specify sequence length instead of assuming 2048 (#52)
|
3 lat temu |
justheuristic
|
a2634001e9
Reduce vocabulary size in test model, fix bug in routing when overlapped (#45)
|
3 lat temu |
Artem Chumachenko
|
d989b94614
Pack of Inference Changes (#37)
|
3 lat temu |
justheuristic
|
f0cffbf67e
Miscellaneous fixes to automatic tests (#35)
|
3 lat temu |
justheuristic
|
f0c7383181
Implement RemoteSequential slicing and extra repr, add tests (#30)
|
3 lat temu |
justheuristic
|
e2711a033b
Add automated tests (#23)
|
3 lat temu |
justheuristic
|
4eadd00a2c
rm prefix from tests
|
3 lat temu |
justheuristic
|
e32208c954
black-isort
|
3 lat temu |
justheuristic
|
4ad845bce3
black-isort
|
3 lat temu |
Dmitry Baranchuk
|
e66ab6f1f2
design interface & refactoring
|
3 lat temu |
justheuristic
|
a6c4a606e0
compare logits to logits
|
3 lat temu |
justheuristic
|
d0c7f2a886
test full model exact match
|
3 lat temu |