Commit graph

618 commits

Author SHA1 Message Date
qwopqwop200
eb5a27f48c
Update basic_usage_wikitext2.py 2023-04-29 18:18:35 +09:00
qwopqwop200
3b74c9758e
change save name 2023-04-29 18:18:21 +09:00
qwopqwop200
b5eb906ac9
change save name 2023-04-29 18:17:59 +09:00
qwopqwop200
05733ae482
change save the name 2023-04-29 18:17:33 +09:00
qwopqwop200
1792cd1111
change save the name 2023-04-29 18:16:48 +09:00
ZXED
24a371d14a
use the same Optional style as in other params 2023-04-29 09:52:11 +03:00
ZXED
c22770188d
allow user to set trust_remote_code flag manually 2023-04-29 09:52:11 +03:00
ZXED
b3f19a7ba7
support custom model name when loading the model 2023-04-29 09:52:11 +03:00
ZXED
ea8ab73343
support custom quantize_config when loading the model 2023-04-29 09:51:50 +03:00
PanQiWei
16d8dd200f remove non-parameters module from MOSSGPTQForCausalLM.outside_layer_modules 2023-04-29 10:58:29 +08:00
PanQiWei
d9e7363fa8 update README.md 2023-04-29 01:47:40 +08:00
PanQiWei
b490ab004e remove override of _resize_attention_mask for llama and opt 2023-04-28 23:08:42 +08:00
潘其威(William)
1d91fded6c
Merge pull request #31 from PanQiWei/add-raise-exception-and-gpt2-xl-example-add
Add example to use with GPT2-XL and raise an error when infeature and outfeature are not be divisible by 256
2023-04-28 22:52:18 +08:00
qwopqwop200
ae8b1a22a3
change global to local 2023-04-28 23:18:39 +09:00
qwopqwop200
e914b9b1bd
update support 256 not div 2023-04-28 22:48:23 +09:00
qwopqwop200
c9215a1b5b
change div num 2023-04-28 22:42:29 +09:00
qwopqwop200
7a38c2a6ef
add basic_usage_gpt_xl 2023-04-28 22:32:46 +09:00
qwopqwop200
19f167e58b
add raise-exception 2023-04-28 22:24:44 +09:00
潘其威(William)
1e353a8dc5
Merge pull request #24 from PanQiWei/speedup_quantization
Offloading and Multiple devices quantization/inference
2023-04-28 18:50:12 +08:00
PanQiWei
5055d785b6 update README.md 2023-04-28 18:44:06 +08:00
PanQiWei
3f761568a8 update example code 2023-04-28 18:26:16 +08:00
PanQiWei
bdb713b5a3 add batch_size to model.quant() api 2023-04-28 18:26:07 +08:00
PanQiWei
41564a48db make data_utils.py as global utils 2023-04-28 18:08:58 +08:00
PanQiWei
e189d91004 update example code 2023-04-28 17:56:52 +08:00
PanQiWei
3dfc87bec3 return module in .to function 2023-04-28 17:20:46 +08:00
PanQiWei
789f821e6c update example code 2023-04-28 17:17:38 +08:00
PanQiWei
a69a73a22c fix device mismatch when directly using model to inference after quantization 2023-04-28 16:41:46 +08:00
PanQiWei
892eeb40e0 update example code 2023-04-28 16:23:02 +08:00
潘其威(William)
092bd502d0
Merge pull request #29 from PanQiWei/fix-bug-speedup_quant
Fix bug speedup quant and support gpt2
2023-04-28 12:02:55 +08:00
qwopqwop200
c4f82ac628
Merge pull request #30 from PanQiWei/add-gpt2
Add gpt2
2023-04-28 09:19:20 +09:00
qwopqwop200
329a64ed40
support conv1d,conv2d 2023-04-28 09:15:42 +09:00
qwopqwop200
bb9afe8b61
support conv1d,conv2d 2023-04-28 09:15:13 +09:00
qwopqwop200
c1b7c7647d
support conv1d 2023-04-28 09:14:44 +09:00
qwopqwop200
ac41f68532
add gpt2 2023-04-28 09:14:05 +09:00
qwopqwop200
dad249990c
add gpt2 2023-04-28 09:13:22 +09:00
qwopqwop200
435eebee4b
support conv1d,conv2d 2023-04-28 09:13:00 +09:00
qwopqwop200
cc0f71a568
add gpt2 2023-04-28 09:11:50 +09:00
qwopqwop200
3f90a22632
fix bug 2023-04-28 08:26:58 +09:00
qwopqwop200
9c38393e31
fix bug about wf meta device 2023-04-28 08:26:11 +09:00
PanQiWei
d0cd5af5d3 make code more robust 2023-04-28 01:29:12 +08:00
PanQiWei
51d2e53130 add support to cpu offloading and multi gpus inference on quantized model 2023-04-28 00:53:57 +08:00
PanQiWei
9c44365836 Merge remote-tracking branch 'origin/speedup_quantization' into speedup_quantization 2023-04-28 00:31:03 +08:00
PanQiWei
48737db0ff update setup.py 2023-04-28 00:30:51 +08:00
PanQiWei
3aac76e71a align 'from_pretrained' api 2023-04-28 00:30:05 +08:00
PanQiWei
b14dca9207 disk offload assertion 2023-04-27 21:31:53 +08:00
PanQiWei
7a3397e7ba add cpu offload when doing quantization 2023-04-27 21:25:24 +08:00
PanQiWei
ac3f7054e0 big fix 2023-04-27 19:33:25 +08:00
PanQiWei
498de923f2 support multi gpus quantization 2023-04-27 18:48:43 +08:00
潘其威(William)
a21205f609
Merge pull request #23 from PanQiWei/add-option
add option
2023-04-27 16:51:33 +08:00
qwopqwop200
8b6ee04aee
add option 2023-04-27 17:29:36 +09:00