Commit Graph

53 Commits

Author SHA1 Message Date
Julien Chaumond
a56ef2a942
make torch.load a bit safer (#4448) 2023-11-02 14:07:08 -03:00
oobabooga
839a87bac8 Fix is_ccl_available & is_xpu_available imports 2023-10-26 20:27:04 -07:00
Abhilash Majumder
778a010df8
Intel Gpu support initialization (#4340) 2023-10-26 23:39:51 -03:00
jllllll
d7ee4c2386
Remove unused import 2023-08-10 00:10:14 -05:00
jllllll
bee73cedbd
Streamline GPTQ-for-LLaMa support 2023-08-09 23:42:34 -05:00
oobabooga
e116d31180 Prevent unwanted log messages from modules 2023-05-21 22:42:34 -03:00
oobabooga
9d5025f531 Improve error handling while loading GPTQ models 2023-05-19 11:20:08 -03:00
oobabooga
b667ffa51d Simplify GPTQ_loader.py 2023-05-17 16:22:56 -03:00
oobabooga
fb91c07191 Minor bug fix 2023-05-17 11:16:37 -03:00
Alex "mcmonkey" Goodwin
1f50dbe352
Experimental jank multiGPU inference that's 2x faster than native somehow (#2100) 2023-05-17 10:41:09 -03:00
oobabooga
2eeb27659d Fix bug in --cpu-memory 2023-05-12 06:17:07 -03:00
oobabooga
3316e33d14 Remove unused code 2023-05-10 11:59:59 -03:00
oobabooga
dfd9ba3e90 Remove duplicate code 2023-05-10 02:07:22 -03:00
minipasila
334486f527
Added instruct-following template for Metharme (#1679) 2023-05-09 22:29:22 -03:00
Carl Kenner
814f754451
Support for MPT, INCITE, WizardLM, StableLM, Galactica, Vicuna, Guanaco, and Baize instruction following (#1596) 2023-05-09 20:37:31 -03:00
IJumpAround
020fe7b50b
Remove mutable defaults from function signature. (#1663) 2023-05-08 22:55:41 -03:00
Matthew McAllister
d78b04f0b4
Add error message when GPTQ-for-LLaMa import fails (#1871)
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-05-08 22:29:09 -03:00
camenduru
ba65a48ec8
trust_remote_code=shared.args.trust_remote_code (#1891) 2023-05-07 17:42:44 -03:00
oobabooga
b6ff138084 Add --checkpoint argument for GPTQ 2023-05-04 15:17:20 -03:00
oobabooga
95d04d6a8d Better warning messages 2023-05-03 21:43:17 -03:00
Wojtab
12212cf6be
LLaVA support (#1487) 2023-04-23 20:32:22 -03:00
oobabooga
7438f4f6ba Change GPTQ triton default settings 2023-04-22 12:27:30 -03:00
USBhost
e1aa9d5173
Support upstream GPTQ once again. (#1451) 2023-04-21 12:43:56 -03:00
sgsdxzy
b57ffc2ec9
Update to support GPTQ triton commit c90adef (#1229) 2023-04-17 01:11:18 -03:00
oobabooga
39099663a0
Add 4-bit LoRA support (#1200) 2023-04-16 23:26:52 -03:00
oobabooga
a75e02de4d Simplify GPTQ_loader.py 2023-04-13 12:13:07 -03:00
oobabooga
ca293bb713 Show a warning if two quantized models are found 2023-04-13 12:04:27 -03:00
oobabooga
fde6d06167 Prioritize names with the groupsize in them 2023-04-13 11:27:03 -03:00
oobabooga
f2bf1a2c9e Add some comments, remove obsolete code 2023-04-13 11:17:32 -03:00
Light
da74cd7c44 Generalized weight search path. 2023-04-13 21:43:32 +08:00
Light
cf58058c33 Change warmup_autotune to a negative switch. 2023-04-13 20:59:49 +08:00
Light
a405064ceb Better dispatch. 2023-04-13 01:48:17 +08:00
Light
f3591ccfa1 Keep minimal change. 2023-04-12 23:26:06 +08:00
oobabooga
8c6155251a More robust 4-bit model loading 2023-04-09 23:19:28 -03:00
oobabooga
ea6e77df72
Make the code more like PEP8 for readability (#862) 2023-04-07 00:15:45 -03:00
EyeDeck
39f3fec913
Broaden GPTQ-for-LLaMA branch support (#820) 2023-04-06 12:16:48 -03:00
oobabooga
3d6cb5ed63 Minor rewrite 2023-04-05 01:21:40 -03:00
oobabooga
f3a2e0b8a9 Disable pre_layer when the model type is not llama 2023-04-05 01:19:26 -03:00
catalpaaa
4ab679480e
allow quantized model to be loaded from model dir (#760) 2023-04-04 23:19:38 -03:00
OWKenobi
ee4547cd34
Detect "vicuna" as llama model type (#772) 2023-04-04 13:23:27 -03:00
oobabooga
1cb9246160 Adapt to the new model names 2023-03-29 21:47:36 -03:00
oobabooga
010b259dde Update documentation 2023-03-28 17:46:00 -03:00
oobabooga
0bec15ebcd Reorder imports 2023-03-28 17:34:15 -03:00
Maya Eary
41ec682834 Disable kernel threshold for gpt-j 2023-03-28 22:45:38 +03:00
Maya Eary
1c075d8d21 Fix typo 2023-03-28 20:43:50 +03:00
Maya Eary
c8207d474f Generalized load_quantized 2023-03-28 20:38:55 +03:00
oobabooga
49c10c5570
Add support for the latest GPTQ models with group-size (#530)
**Warning: old 4-bit weights will not work anymore!**

See here how to get up to date weights: https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model#step-2-get-the-pre-converted-weights
2023-03-26 00:11:33 -03:00
EyeDeck
dcfd866402 Allow loading of .safetensors through GPTQ-for-LLaMa 2023-03-23 21:31:34 -04:00
oobabooga
db4219a340
Update comments 2023-03-20 16:40:08 -03:00
oobabooga
7618f3fe8c
Add -gptq-preload for 4-bit offloading (#460)
This works in a 4GB card now:

```
python server.py --model llama-7b-hf --gptq-bits 4 --gptq-pre-layer 20
```
2023-03-20 16:30:56 -03:00