 justheuristic
|
a59e38a578
running inference session with position getter/setter (#594)
|
1 éve |
 xtinkt
|
9aecb3f39e
style
|
1 éve |
|
xtinkt
|
269028d0e6
fix
|
1 éve |
|
xtinkt
|
7565ddee81
fix
|
1 éve |
|
xtinkt
|
10de34b72a
fix
|
1 éve |
|
xtinkt
|
de2c38ab1b
fix
|
1 éve |
|
xtinkt
|
b6801af79d
fix
|
1 éve |
|
xtinkt
|
4285ddbd7b
fix
|
1 éve |
 Anton Sinitsin
|
68585864ae
Update transformers to 4.41.2 (#583)
|
1 éve |
 Priyanshupareek
|
e268c99a6b
Restrict PyTorch version to <2.3.0 to resolve import error (#577)
|
1 éve |
 Artem Chumachenko
|
30f522d1a0
Fix dummy cache allocation (#574)
|
1 éve |
|
Artem Chumachenko
|
d6f4f80f3f
Fix Mixtral-related issues (#570)
|
1 éve |
|
Artem Chumachenko
|
d2fcbbc72e
Add Mixtral models (#553)
|
1 éve |
|
justheuristic
|
2ad0b2b936
Fix p2p pushing in rpc_inference (by @miaoqijun ) , support transformers 4.38.2 (#563)
|
1 éve |
|
justheuristic
|
efee5d1fa8
Clean disk space in push-docker-image.yaml (#558)
|
1 éve |
 Denis Mazur
|
0d91bbdac3
Bump transformers and accelerate versions (#554)
|
1 éve |
|
justheuristic
|
d59c15c578
Bump version for inference diagnostics (#543)
|
1 éve |
 Max Ryabinin
|
03cbe90234
Optimize LLaMA for inference (#513)
|
1 éve |
|
justheuristic
|
25a0796b39
Hotfix: require peft version 0.5.0 (#539)
|
1 éve |
|
justheuristic
|
dcce43670f
Hotfix: set transformers version <=4.34 temporarily (#538)
|
1 éve |
 Alexander Borzunov
|
82a97d6e9e
Fix beam search in GPU clients (#531)
|
1 éve |
|
Alexander Borzunov
|
47d50e1e29
Improve default arguments for clients and servers (#530)
|
1 éve |
|
Max Ryabinin
|
ae19b65095
Add position_ids argument to DistributedFalconModel (#525)
|
1 éve |
|
Alexander Borzunov
|
1d9401ddce
Update README.md (#520)
|
1 éve |
 FYY
|
a2484b3053
Fix file locks in NFS-mounted directories (#517)
|
1 éve |
|
Alexander Borzunov
|
5ce4f1a159
Store (start_block, end_block) in each DHT record for reliability (#510)
|
1 éve |
|
Alexander Borzunov
|
158621677b
Bump version to 2.2.0 (#502)
|
2 éve |
|
Max Ryabinin
|
1ebd88ae7b
Optimize the Falcon block for inference (#500)
|
2 éve |
|
Alexander Borzunov
|
d40eb6c701
Fix prompt tuning after #464 (#501)
|
2 éve |
|
Alexander Borzunov
|
dd4a3230bc
Add Falcon support (#499)
|
2 éve |
