Commit graph

308 commits

Author SHA1 Message Date
PanQiWei
ad10c13d40 support AdaLora 2023-05-28 21:30:45 +08:00
PanQiWei
3ee2daa73c make GPTQLoraModel to inherit from LoraModel to simplify code 2023-05-28 17:36:18 +08:00
PanQiWei
22d1d8dcaa add 'auto_find_all_linears' argument to get_gptq_peft_model function 2023-05-28 17:04:38 +08:00
PanQiWei
83132a663a add warning to guide users interact with lora properly 2023-05-28 16:57:31 +08:00
PanQiWei
86f060c74b Merge branch 'main' into peft_integration 2023-05-28 16:23:38 +08:00
PanQiWei
491da62402 fix signature at import time 2023-05-27 17:49:58 +08:00
潘其威(William)
23998345f5
Merge branch 'main' into falcon 2023-05-27 16:23:16 +08:00
Bill Cai
0729760234
Update auto.py 2023-05-27 11:16:43 +08:00
潘其威(William)
269ef7335c
Merge branch 'main' into falcon 2023-05-27 08:15:52 +08:00
潘其威(William)
3c3b0e1e79
Merge branch 'main' into GPTBigCode 2023-05-27 08:03:03 +08:00
潘其威(William)
eab728b263
Merge branch 'main' into Codegen 2023-05-27 08:00:19 +08:00
潘其威(William)
f6fd314d5a
Merge branch 'main' into GPTBigCode 2023-05-27 07:57:25 +08:00
qwopqwop200
277809381b
fix bug 2023-05-27 08:53:47 +09:00
PanQiWei
5bc5325920 add find_all_linear_names help function, make customized lora module more general 2023-05-27 07:49:17 +08:00
PanQiWei
eb9c0b140f update FusedLlamaMLPForQuantizedModel for general usage purpose 2023-05-27 07:47:20 +08:00
qwopqwop200
bcb345fb35
support falcon 2023-05-27 07:53:39 +09:00
qwopqwop200
4d5b4fa5c6
add dtype 2023-05-27 07:49:28 +09:00
qwopqwop200
c14b4c1567
change find layer algorithm 2023-05-27 07:48:50 +09:00
PanQiWei
f7e705848a move peft compatible model injection to the last step 2023-05-26 14:29:33 +08:00
PanQiWei
8bf21a7e4c set xavier_uniform_ as lora_A's init function 2023-05-26 14:06:53 +08:00
PanQiWei
2b532f9453 add trainable mode 2023-05-26 13:11:30 +08:00
PanQiWei
fe5f5d12ed Merge branch 'main' into peft_integration 2023-05-26 09:48:06 +08:00
PanQiWei
69609c4bc7 support faster vecquant4matmul cuda kernel 2023-05-26 08:55:05 +08:00
PanQiWei
cfd27e8caa refactor file structure of qlinears 2023-05-26 07:18:16 +08:00
qwopqwop200
503f85255d
Update kernels.py 2023-05-25 23:15:33 +09:00
PanQiWei
f6a34137e9 lora compatibility 2023-05-25 19:44:53 +08:00
PanQiWei
d293bf3a04 first upload peft_utils.py 2023-05-25 15:11:11 +08:00
PanQiWei
4d157a3b64 add hack of __getattr__ 2023-05-25 15:10:33 +08:00
TheBloke
b7bb50b4d5 Fix bug added after merge 2023-05-25 07:05:51 +01:00
Tom Jobbins
492255b400
Merge branch 'main' into TheBloke_support-HF-download 2023-05-25 07:02:13 +01:00
PanQiWei
096749fe9d generalize QuantLinear 2023-05-25 13:33:09 +08:00
PanQiWei
94ef4d5ada update basic usage example code 2023-05-24 17:56:46 +08:00
PanQiWei
c89bb6450c correct typo of function name 2023-05-24 17:43:38 +08:00
PanQiWei
10347fdd7b remove full_cpu_offload argument and unify model dispatch strategy 2023-05-24 17:41:04 +08:00
PanQiWei
379f24c2a5 remove add_align_logits_hook_to_model 2023-05-24 17:01:57 +08:00
PanQiWei
749dba1a7e disable add_align_logits_hook_to_model for now 2023-05-24 13:42:06 +08:00
PanQiWei
58c1b509f0 support add_align_logits_hook_to_model 2023-05-24 12:50:30 +08:00
PanQiWei
21ab7c435a make comments more readable 2023-05-24 11:38:29 +08:00
PanQiWei
c31b370228 make_sure_not_tensor_in_meta_device before load checkpoint 2023-05-24 11:32:45 +08:00
PanQiWei
63f1b4e073 remove comment 2023-05-24 11:23:07 +08:00
PanQiWei
057c39e3f2 fix meta device bug when use low_cpu_mem_usage 2023-05-24 11:19:59 +08:00
PanQiWei
e2e7809a1f always to enable QuantLinear bias to make compatible with model quantized from other frameworks 2023-05-24 10:56:31 +08:00
PanQiWei
8e034b28bc remove duplicate code 2023-05-23 23:48:15 +08:00
PanQiWei
4373d6b29c Merge branch 'main' into improve_cpu_offload 2023-05-23 23:47:33 +08:00
PanQiWei
191da8141e fix device mismatch 2023-05-23 23:22:52 +08:00
PanQiWei
e4e90e8b0a add warmup_triton method 2023-05-23 23:18:46 +08:00
PanQiWei
ed14d3a786 fix save quantized model failed when load pretrained model using CPU offload 2023-05-23 23:17:11 +08:00
PanQiWei
6476ee4235 add options: 'low_cpu_mem_usage' and 'full_cpu_offload' 2023-05-23 22:51:00 +08:00
PanQiWei
1b2159bd4c add more help functions 2023-05-23 19:30:28 +08:00
PanQiWei
db63c0876a half out 2023-05-23 16:08:28 +08:00