Commit graph

66 commits

Author SHA1 Message Date
PanQiWei
db9eabfc4b add disable_exllama argument 2023-08-09 12:05:15 +08:00
PanQiWei
ff1f100ded remove argument 'save_dir' in method from_quantized 2023-07-26 17:58:04 +08:00
PanQiWei
722a621aaa simplified code 2023-07-26 17:53:47 +08:00
潘其威(William)
fd24e84eb2
Merge pull request #166 from casperbh96/main
[FEATURE] Implement perplexity metric to compare against llama.cpp
2023-07-26 14:04:51 +08:00
Casper
1949e8607d Fix usage of device 2023-06-19 20:16:16 +02:00
Casper
5b88f03bba Create example of how to evaluate perplexity 2023-06-19 20:03:42 +02:00
Marisa Kirisame
ae80f2dc72 fix stale documentation 2023-06-14 20:04:27 +00:00
潘其威(William)
bf521cbe7b
Merge pull request #134 from TheBloke/TB_benchmark
add command flags inject_fused_attention and inject_fused_mlp
2023-06-05 23:02:36 +08:00
TheBloke
edb13d493e Default inject_fused_attention and mlp to True, matching defaults 2023-06-03 17:58:40 +01:00
TheBloke
4617629f0c Support setting inject_fused_attention and inject_fused_mlp to False 2023-06-03 17:48:36 +01:00
潘其威(William)
b4fdd8d264
Merge branch 'main' into peft_integration 2023-06-02 19:11:59 +08:00
PanQiWei
e826d89dbc update basic_usage.py 2023-05-30 07:47:10 +08:00
PanQiWei
448a53e6a7 delete push to hub example script 2023-05-30 07:39:58 +08:00
PanQiWei
9dd7784e6a update lr 2023-05-29 21:27:35 +08:00
PanQiWei
539682e951 update lr 2023-05-28 22:54:53 +08:00
PanQiWei
788128f0a6 rename example scripts 2023-05-28 22:49:01 +08:00
PanQiWei
4296ced96d add example script for AdaptionPrompt peft type 2023-05-28 22:44:32 +08:00
PanQiWei
7af93624d7 remove useless code 2023-05-28 22:30:38 +08:00
PanQiWei
a1f5204bfd fix ppl calculation error 2023-05-28 22:20:49 +08:00
PanQiWei
7bb01ae1cd remove useless prints 2023-05-28 22:01:35 +08:00
PanQiWei
956029fcb2 update README.md 2023-05-28 21:42:59 +08:00
PanQiWei
271ae2926b add training example scripts for Lora and AdaLora 2023-05-28 21:35:53 +08:00
PanQiWei
801b1c13ca update example script 2023-05-28 21:30:53 +08:00
PanQiWei
f703c9ac98 update generation_speed.py 2023-05-27 20:15:43 +08:00
PanQiWei
1ff000658e update README.md 2023-05-27 19:26:56 +08:00
PanQiWei
e8bd3c33c4 add generation speed benchmark example script 2023-05-27 19:16:42 +08:00
PanQiWei
3cb1bf5a6d add trust_remote_code command line flag 2023-05-27 17:09:10 +08:00
qwopqwop200
874c9fd0ef
fix bug 2023-05-27 07:47:17 +09:00
PanQiWei
94ef4d5ada update basic usage example code 2023-05-24 17:56:46 +08:00
PanQiWei
b803369719 update quant_with_alpaca.py 2023-05-20 16:43:21 +08:00
PanQiWei
f78f074409 update quant_with_alpaca.py 2023-05-20 16:42:34 +08:00
Forkoz
cc835640a9
Update some help 2023-05-17 07:31:09 -05:00
Forkoz
6b0b84bc9b
Update basic_usage_gpt_xl.py 2023-05-17 07:28:53 -05:00
Forkoz
2d0aaa423f
update another example 2023-05-17 07:27:49 -05:00
Forkoz
922ec02998
Fix another example 2023-05-17 07:26:24 -05:00
Forkoz
eaac7a7b76
Update example script to include desc_act
It will help with people unwittingly making incompatible models.
2023-05-15 11:26:22 +00:00
qwopqwop200
d986a738e1
bug fix quantization demo 2023-05-01 08:03:11 +09:00
PanQiWei
ff20acaafe add quick start tutorial 2023-04-29 22:31:42 +08:00
qwopqwop200
9317af6c40
change save name 2023-04-29 18:19:13 +09:00
qwopqwop200
605f345135
Update basic_usage_gpt_xl.py 2023-04-29 18:18:50 +09:00
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
7a38c2a6ef
add basic_usage_gpt_xl 2023-04-28 22:32:46 +09:00
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
e189d91004 update example code 2023-04-28 17:56:52 +08:00
PanQiWei
789f821e6c update example code 2023-04-28 17:17:38 +08:00
PanQiWei
892eeb40e0 update example code 2023-04-28 16:23:02 +08:00