SeanScripts
|
e1338a1804
|
Add whisper turbo (#6423)
|
2024-10-01 17:49:35 -03:00 |
|
oobabooga
|
49dfa0adaf
|
Fix the "save preset" event
|
2024-10-01 11:20:48 -07:00 |
|
oobabooga
|
93c250b9b6
|
Add a UI element for enable_tp
|
2024-10-01 11:16:15 -07:00 |
|
oobabooga
|
d364aa0a3c
|
Lint
|
2024-10-01 10:22:57 -07:00 |
|
oobabooga
|
cca9d6e22d
|
Lint
|
2024-10-01 10:21:06 -07:00 |
|
oobabooga
|
c6b50f88da
|
Lint
|
2024-10-01 10:19:28 -07:00 |
|
oobabooga
|
7cb98351da
|
Merge branch 'main' into dev
|
2024-10-01 14:18:32 -03:00 |
|
oobabooga
|
617cd7b705
|
Revert "Update accelerate requirement from ==0.33.* to ==0.34.* (#6416)"
This reverts commit 6063a66414 .
|
2024-10-01 09:06:25 -07:00 |
|
dependabot[bot]
|
6063a66414
|
Update accelerate requirement from ==0.33.* to ==0.34.* (#6416)
|
2024-09-30 18:50:38 -03:00 |
|
oobabooga
|
4d9ce586d3
|
Update llama_cpp_python_hijack.py, fix llamacpp_hf
|
2024-09-30 14:49:21 -07:00 |
|
oobabooga
|
9ca0cd7749
|
Bump llama-cpp-python to 0.3.1
|
2024-09-29 20:47:04 -07:00 |
|
oobabooga
|
bbdeed3cf4
|
Make sampler priority high if unspecified
|
2024-09-29 20:45:27 -07:00 |
|
oobabooga
|
01362681f2
|
Bump exllamav2 to 0.2.4
|
2024-09-29 07:42:44 -07:00 |
|
Hanusz Leszek
|
e4b0467f9f
|
Add beforeunload event to add confirmation dialog when leaving page (#6279)
|
2024-09-29 01:14:19 -03:00 |
|
Manuel Schmid
|
0f90a1b50f
|
Do not set value for histories in chat when --multi-user is used (#6317)
|
2024-09-29 01:08:55 -03:00 |
|
oobabooga
|
055f3f5632
|
Fix after #6386 (thanks @Touch-Night)
|
2024-09-28 20:55:26 -07:00 |
|
oobabooga
|
57160cd6fa
|
Update README
|
2024-09-28 20:50:41 -07:00 |
|
oobabooga
|
3f0571b62b
|
Update README
|
2024-09-28 20:48:30 -07:00 |
|
oobabooga
|
3fb02f43f6
|
Update README
|
2024-09-28 20:38:43 -07:00 |
|
oobabooga
|
3b99532e02
|
Remove HQQ and AQLM from requirements
|
2024-09-28 20:34:59 -07:00 |
|
oobabooga
|
c61b29b9ce
|
Simplify the warning when flash-attn fails to import
|
2024-09-28 20:33:17 -07:00 |
|
oobabooga
|
b92d7fd43e
|
Add warnings for when AutoGPTQ, TensorRT-LLM, or HQQ are missing
|
2024-09-28 20:30:24 -07:00 |
|
oobabooga
|
65e5864084
|
Update README
|
2024-09-28 20:25:26 -07:00 |
|
oobabooga
|
1a870b3ea7
|
Remove AutoAWQ and AutoGPTQ from requirements (no wheels available)
|
2024-09-28 19:38:56 -07:00 |
|
oobabooga
|
85994e3ef0
|
Bump pytorch to 2.4.1
|
2024-09-28 09:44:08 -07:00 |
|
oobabooga
|
ca5a2dba72
|
Bump rocm to 6.1.2
|
2024-09-28 09:39:53 -07:00 |
|
oobabooga
|
7276dca933
|
Fix a typo
|
2024-09-27 20:28:17 -07:00 |
|
RandoInternetPreson
|
46996f6519
|
ExllamaV2 tensor parallelism to increase multi gpu inference speeds (#6356)
|
2024-09-28 00:26:03 -03:00 |
|
Philipp Emanuel Weidmann
|
301375834e
|
Exclude Top Choices (XTC): A sampler that boosts creativity, breaks writing clichés, and inhibits non-verbatim repetition (#6335)
|
2024-09-27 22:50:12 -03:00 |
|
oobabooga
|
3492e33fd5
|
Bump bitsandbytes to 0.44
|
2024-09-27 16:59:30 -07:00 |
|
Thireus ☠
|
626b0a0437
|
Force /bin/bash shell for conda (#6386)
|
2024-09-27 19:47:04 -03:00 |
|
oobabooga
|
5c918c5b2d
|
Make it possible to sort DRY
|
2024-09-27 15:40:48 -07:00 |
|
oobabooga
|
78b8705400
|
Bump llama-cpp-python to 0.3.0 (except for AMD)
|
2024-09-27 15:06:31 -07:00 |
|
oobabooga
|
c5f048e912
|
Bump ExLlamaV2 to 0.2.2
|
2024-09-27 15:04:08 -07:00 |
|
oobabooga
|
7424f789bf
|
Fix the sampling monkey patch (and add more options to sampler_priority) (#6411)
|
2024-09-27 19:03:25 -03:00 |
|
oobabooga
|
c497a32372
|
Bump transformers to 4.45
|
2024-09-26 11:55:51 -07:00 |
|
oobabooga
|
f98431c744
|
Apply the change to all requirements (oops)
|
2024-09-06 18:48:13 -07:00 |
|
oobabooga
|
a50477ec85
|
Apply the change to all requirements (oops)
|
2024-09-06 18:47:25 -07:00 |
|
oobabooga
|
ac30b004ef
|
Pin fastapi/pydantic requirement versions
|
2024-09-06 18:45:15 -07:00 |
|
oobabooga
|
e86ab37aaf
|
Merge remote-tracking branch 'refs/remotes/origin/dev' into dev
|
2024-09-06 18:44:43 -07:00 |
|
oobabooga
|
27797a92d0
|
Pin fastapi/pydantic requirement versions
|
2024-09-06 18:38:57 -07:00 |
|
Jean-Sylvain Boige
|
4924ee2901
|
typo in OpenAI response format (#6365)
|
2024-09-05 21:42:23 -03:00 |
|
oobabooga
|
bba5b36d33
|
Don't import PEFT unless necessary
|
2024-09-03 19:40:53 -07:00 |
|
oobabooga
|
c5b40eb555
|
llama.cpp: prevent prompt evaluation progress bar with just 1 step
|
2024-09-03 17:37:06 -07:00 |
|
oobabooga
|
2cb8d4c96e
|
Bump llama-cpp-python to 0.2.90
|
2024-09-03 05:53:18 -07:00 |
|
oobabooga
|
64919e0d69
|
Bump flash-attention to 2.6.3
|
2024-09-03 05:51:46 -07:00 |
|
oobabooga
|
68d52c60f3
|
Merge remote-tracking branch 'refs/remotes/origin/dev' into dev
|
2024-09-02 21:16:39 -07:00 |
|
oobabooga
|
d1168afa76
|
Bump ExLlamaV2 to 0.2.0
|
2024-09-02 21:15:51 -07:00 |
|
Stefan Merettig
|
9a150c3368
|
API: Relax multimodal format, fixes HuggingFace Chat UI (#6353)
|
2024-09-02 23:03:15 -03:00 |
|
GralchemOz
|
4c74c7a116
|
Fix UnicodeDecodeError for BPE-based Models (especially GLM-4) (#6357)
|
2024-09-02 23:00:59 -03:00 |
|