Commit Graph

597 Commits

Author SHA1 Message Date
Shouyi
031fe7225e
Add tensor split support for llama.cpp (#3171) 2023-07-25 18:59:26 -03:00
oobabooga
7bc408b472 Change rms_norm_eps to 5e-6 for llama-2-70b ggml
Based on https://github.com/ggerganov/llama.cpp/pull/2384
2023-07-25 14:54:57 -07:00
oobabooga
08c622df2e Autodetect rms_norm_eps and n_gqa for llama-2-70b 2023-07-24 15:27:34 -07:00
oobabooga
a07d070b6c
Add llama-2-70b GGML support (#3285) 2023-07-24 16:37:03 -03:00
jllllll
d7a14174a2
Remove auto-loading when only one model is available (#3187) 2023-07-18 11:39:08 -03:00
oobabooga
f83fdb9270 Don't reset LoRA menu when loading a model 2023-07-17 12:50:25 -07:00
oobabooga
2de0cedce3 Fix reload screen color 2023-07-15 22:39:39 -07:00
oobabooga
27a84b4e04 Make AutoGPTQ the default again
Purely for compatibility with more models.
You should still use ExLlama_HF for LLaMA models.
2023-07-15 22:29:23 -07:00
oobabooga
5e3f7e00a9
Create llamacpp_HF loader (#3062) 2023-07-16 02:21:13 -03:00
Panchovix
7c4d4fc7d3
Increase alpha value limit for NTK RoPE scaling for exllama/exllama_HF (#3149) 2023-07-16 01:56:04 -03:00
oobabooga
b284f2407d Make ExLlama_HF the new default for GPTQ 2023-07-14 14:03:56 -07:00
oobabooga
22341e948d Merge branch 'main' into dev 2023-07-12 14:19:49 -07:00
oobabooga
0e6295886d Fix lora download folder 2023-07-12 14:19:33 -07:00
oobabooga
eb823fce96 Fix typo 2023-07-12 13:55:19 -07:00
oobabooga
d0a626f32f Change reload screen color 2023-07-12 13:54:43 -07:00
oobabooga
c592a9b740 Fix #3117 2023-07-12 13:33:44 -07:00
Gabriel Pena
eedb3bf023
Add low vram mode on llama cpp (#3076) 2023-07-12 11:05:13 -03:00
Axiom Wolf
d986c17c52
Chat history download creates more detailed file names (#3051) 2023-07-12 00:10:36 -03:00
Salvador E. Tropea
324e45b848
[Fixed] wbits and groupsize values from model not shown (#2977) 2023-07-11 23:27:38 -03:00
oobabooga
bfafd07f44 Change a message 2023-07-11 18:29:20 -07:00
micsthepick
3708de2b1f
respect model dir for downloads (#3077) (#3079) 2023-07-11 18:55:46 -03:00
oobabooga
9aee1064a3 Block a cloudfare request 2023-07-06 22:24:52 -07:00
oobabooga
40c5722499
Fix #2998 2023-07-04 11:35:25 -03:00
oobabooga
55457549cd Add information about presets to the UI 2023-07-03 22:39:01 -07:00
Panchovix
10c8c197bf
Add Support for Static NTK RoPE scaling for exllama/exllama_hf (#2955) 2023-07-04 01:13:16 -03:00
FartyPants
eb6112d5a2
Update server.py - clear LORA after reload (#2952) 2023-07-04 00:13:38 -03:00
oobabooga
4b1804a438
Implement sessions + add basic multi-user support (#2991) 2023-07-04 00:03:30 -03:00
missionfloyd
ac0f96e785
Some more character import tweaks. (#2921) 2023-06-29 14:56:25 -03:00
oobabooga
5d2a8b31be Improve Parameters tab UI 2023-06-29 14:33:47 -03:00
oobabooga
3443219cbc
Add repetition penalty range parameter to transformers (#2916) 2023-06-29 13:40:13 -03:00
oobabooga
22d455b072 Add LoRA support to ExLlama_HF 2023-06-26 00:10:33 -03:00
oobabooga
b7c627f9a0 Set UI defaults 2023-06-25 22:55:43 -03:00
oobabooga
c52290de50
ExLlama with long context (#2875) 2023-06-25 22:49:26 -03:00
oobabooga
f0fcd1f697 Sort some imports 2023-06-25 01:44:36 -03:00
oobabooga
e6e5f546b8 Reorganize Chat settings tab 2023-06-25 01:10:20 -03:00
jllllll
bef67af23c
Use pre-compiled python module for ExLlama (#2770) 2023-06-24 20:24:17 -03:00
missionfloyd
51a388fa34
Organize chat history/character import menu (#2845)
* Organize character import menu

* Move Chat history upload/download labels
2023-06-24 09:55:02 -03:00
oobabooga
3ae9af01aa Add --no_use_cuda_fp16 param for AutoGPTQ 2023-06-23 12:22:56 -03:00
LarryVRH
580c1ee748
Implement a demo HF wrapper for exllama to utilize existing HF transformers decoding. (#2777) 2023-06-21 15:31:42 -03:00
Morgan Schweers
447569e31a
Add a download progress bar to the web UI. (#2472)
* Show download progress on the model screen.

* In case of error, mark as done to clear progress bar.

* Increase the iteration block size to reduce overhead.
2023-06-20 22:59:14 -03:00
oobabooga
09c781b16f Add modules/block_requests.py
This has become unnecessary, but it could be useful in the future
for other libraries.
2023-06-18 16:31:14 -03:00
oobabooga
44f28830d1 Chat CSS: fix ul, li, pre styles + remove redefinitions 2023-06-18 15:20:51 -03:00
oobabooga
239b11c94b Minor bug fixes 2023-06-17 17:57:56 -03:00
oobabooga
1e400218e9 Fix a typo 2023-06-16 21:01:57 -03:00
oobabooga
5f392122fd Add gpu_split param to ExLlama
Adapted from code created by Ph0rk0z. Thank you Ph0rk0z.
2023-06-16 20:49:36 -03:00
oobabooga
83be8eacf0 Minor fix 2023-06-16 20:38:32 -03:00
oobabooga
9f40032d32
Add ExLlama support (#2444) 2023-06-16 20:35:38 -03:00
oobabooga
dea43685b0 Add some clarifications 2023-06-16 19:10:53 -03:00
oobabooga
7ef6a50e84
Reorganize model loading UI completely (#2720) 2023-06-16 19:00:37 -03:00
Tom Jobbins
646b0c889f
AutoGPTQ: Add UI and command line support for disabling fused attention and fused MLP (#2648) 2023-06-15 23:59:54 -03:00