ilotoki_thu/alpaca_lora_4bit
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Commit Graph

  • 2f704b93c9 add test result main John Smith 2023-04-26 18:02:43 +08:00
  • 73f51188bf Update readme John Smith 2023-04-26 17:53:26 +08:00
  • 97804534b9 fix reference John Smith 2023-04-26 17:29:29 +08:00
  • 8e5cf08479 fix dependency John Smith 2023-04-26 17:17:59 +08:00
  • 42ef3484a9 fix _SentinelTokenStoppingCriteria John Smith 2023-04-26 14:38:57 +08:00
  • d6791790ed fix bug John Smith 2023-04-26 13:13:54 +08:00
  • 1abdc99675 add server John Smith 2023-04-26 12:50:36 +08:00
  • 633c28fd25 add quant attn v1 support John Smith 2023-04-25 12:28:45 +08:00
  • f9c94f27cc fix bug John Smith 2023-04-25 09:21:15 +08:00
  • b5af5c00e1 optimize lora compute John Smith 2023-04-23 20:00:28 +08:00
  • 82bbea2729 optimized matmul for v2 model John Smith 2023-04-22 23:01:39 +08:00
  • 9fe5ab3642 fix bug John Smith 2023-04-22 17:23:24 +08:00
  • 4e42965c0d Merge branch 'main' of github.com:johnsmith0031/alpaca_lora_4bit John Smith 2023-04-22 16:35:37 +08:00
  • eb442494d1 optimize mem usage John Smith 2023-04-22 16:35:18 +08:00
  • 51bf103269 Update README.md John Smith 2023-04-22 16:09:38 +08:00
  • 33a76b00ca Update README.md John Smith 2023-04-22 15:58:06 +08:00
  • de3c91834e optimized attention and mlp for performance, add lora monkey patch for models here and GPTQ_For_Llama models using optimization John Smith 2023-04-22 15:18:54 +08:00
  • 35caccd376 add assert John Smith 2023-04-21 10:24:58 +08:00
  • 1a0c63edaf Update README.md John Smith 2023-04-20 10:04:13 +08:00
  • a0a0962de7 Update README.md John Smith 2023-04-20 09:57:18 +08:00
  • 3b18aa1cc6 fix bug and remove bnb John Smith 2023-04-20 09:51:57 +08:00
  • 90e628121a fix continue training for this version John Smith 2023-04-17 14:16:05 +08:00
  • e64ff9facd fix bug John Smith 2023-04-17 13:42:50 +08:00
  • 7a71b0dd12 fix bug when loading old lora model John Smith 2023-04-17 12:16:21 +08:00
  • 6739f529f5 Merge pull request #79 from wesleysanjose/main John Smith 2023-04-15 00:53:59 +08:00
  • b8e2588fbf Fix Dockerfile for No module named 'monkeypatch' wesleysanjose 2023-04-14 01:27:44 -07:00
  • fb7665726e Update requirements.txt John Smith 2023-04-13 14:44:59 +08:00
  • 9c3058c1de fix bug John Smith 2023-04-13 11:34:53 +08:00
  • 76d7963dff fix bug John Smith 2023-04-13 10:36:57 +08:00
  • 6aab31bd73 update reference John Smith 2023-04-13 10:35:10 +08:00
  • 5ff11b5bf2 Merge pull request #77 from winglian/upstream-peft John Smith 2023-04-13 10:25:05 +08:00
  • f4b1dc19ab addtional fix Wing Lian 2023-04-12 06:54:23 -04:00
  • 17e6a1585f Update README.md John Smith 2023-04-12 13:09:48 +08:00
  • e946f830d4 minor fix John Smith 2023-04-12 13:06:30 +08:00
  • 4261bd8070 add xformers support John Smith 2023-04-12 12:59:44 +08:00
  • 7871baf311 fix bug on v1 finetune John Smith 2023-04-11 19:15:56 +08:00
  • 7762459f1f Merge pull request #74 from andybarry/readme_fix John Smith 2023-04-10 21:38:06 +08:00
  • 68e1b35660 Merge pull request #73 from dnouri/fix-monkeypatch-v1 John Smith 2023-04-10 21:37:27 +08:00
  • e590407c5f Fix readme typo. Andy Barry 2023-04-10 08:56:05 -04:00
  • ee7d94a1f3 Bugfix in custom_monkey_patch for v1 models Daniel Nouri 2023-04-10 12:41:16 +02:00
  • 5d3267d80d add v1 model as default in custom monkey patch John Smith 2023-04-10 09:33:41 +08:00
  • c2b33bacc9 use monkey patch instead of forked peft Wing Lian 2023-04-09 11:40:58 -04:00
  • f185b90c3e Update README.md John Smith 2023-04-09 12:50:49 +08:00
  • 4c18a56fc0 fix bug John Smith 2023-04-09 12:44:50 +08:00
  • 8cf3bd4086 add g_idx support on cuda backend John Smith 2023-04-09 12:26:22 +08:00
  • b73f4e5e64 Merge pull request #64 from andybarry/readme_fix John Smith 2023-04-09 11:15:23 +08:00
  • b5d49cb9b1 Fix URL in readme. Andy Barry 2023-04-08 12:38:45 -04:00
  • 132c67be0d Fix bug John Smith 2023-04-08 23:58:30 +08:00
  • 56e5bf2854 Merge pull request #63 from andybarry/dockerfile John Smith 2023-04-08 15:48:27 +08:00
  • a93cf1264a Add timing on readme, remove useless line in dockerfile. Andy Barry 2023-04-08 01:54:29 -04:00
  • 191d92c940 Clean up diff Andy Barry 2023-04-08 01:27:56 -04:00
  • 31614fc2c4 Move 7bn changes into dockerfile. Andy Barry 2023-04-08 01:21:17 -04:00
  • 2e5aaf6dd6 Merge readmes. Andy Barry 2023-04-08 01:14:54 -04:00
  • e854f5d111 Fix after merge. Andy Barry 2023-04-08 00:53:28 -04:00
  • 8435b2c7f2 Merge branch 'main' of https://github.com/johnsmith0031/alpaca_lora_4bit Andy Barry 2023-04-07 22:02:54 -04:00
  • f91d4cbb59 Update README.md John Smith 2023-04-07 16:10:36 +08:00
  • b01b10eb4d Colorized output John Smith 2023-04-07 15:58:38 +08:00
  • 32904da1ff fix bug on triton matmul John Smith 2023-04-07 15:50:55 +08:00
  • dba3773b30 add triton backend support for v2 model John Smith 2023-04-07 15:34:06 +08:00
  • 9351f49542 merge pull request in new branch John Smith 2023-04-07 10:40:24 +08:00
  • 85e9cf004a Merge pull request #59 from yamashi/main John Smith 2023-04-07 10:05:18 +08:00
  • c5aa7fb695 Update finetune.py yamashi 2023-04-07 00:43:36 +02:00
  • 95cd390d25 Update Finetune4bConfig.py yamashi 2023-04-07 00:43:15 +02:00
  • 778035152d Update arg_parser.py yamashi 2023-04-07 00:42:34 +02:00
  • 2bf5d42f28 Add position_ids to flash attention yamashi 2023-04-06 17:46:15 +02:00
  • 7770e76c9c Fix args of flash attention yamashi 2023-04-06 17:32:01 +02:00
  • 30bf938d03 Update requirements.txt yamashi 2023-04-06 13:50:25 +02:00
  • 7b18b39dd8 Create llama_flash_attn_monkey_patch.py yamashi 2023-04-06 13:49:36 +02:00
  • 3ea18575c7 Use flash attention monkeypatch yamashi 2023-04-06 13:49:12 +02:00
  • 8020b3ec3b Update README.md John Smith 2023-04-06 13:57:32 +08:00
  • 9a02a88fb8 add patch for encode function to remove eos token at the beginning of left side John Smith 2023-04-06 12:56:27 +08:00
  • 3a95ad894b Update README.md Andy Barry 2023-04-06 00:53:57 -04:00
  • 1b8b6e193c Merge branch 'main' of github.com:andybarry/alpaca_lora_4bit_docker Andy Barry 2023-04-06 00:31:29 -04:00
  • 3076eaf4aa Add gif. Andy Barry 2023-04-06 00:30:28 -04:00
  • 0a51b6b0ee Update README.md Andy Barry 2023-04-06 00:20:30 -04:00
  • 6130b9bd0f Update README.md Andy Barry 2023-04-06 00:06:29 -04:00
  • 0f25304184 Update README.md Andy Barry 2023-04-06 00:06:05 -04:00
  • 242fc92e54 Fix url Andy Barry 2023-04-05 23:38:28 -04:00
  • fa966018f4 Fix docker run command. Andy Barry 2023-04-05 23:38:00 -04:00
  • 1af4023883 Fix some issues. Andy Barry 2023-04-05 23:29:10 -04:00
  • 417eba372a Add dockerfile and change some numbers to use 7bn model. Andy Barry 2023-04-05 23:13:35 -04:00
  • 085d9556f9 fix bug John Smith 2023-04-06 10:46:42 +08:00
  • c991e2a091 Delete triton_test.py Andrey Glushenkov 2023-04-06 02:39:40 +03:00
  • 0d271d5d90 Add files via upload Andrey Glushenkov 2023-04-06 02:38:06 +03:00
  • 4a2d23aa29 Delete autograd_4bit.py Andrey Glushenkov 2023-04-06 02:31:06 +03:00
  • f20570343f GPTQv2 support Andrey Glushenkov 2023-04-06 02:29:36 +03:00
  • 86387a0a35 update multi gpu support in finetune.py John Smith 2023-04-03 23:55:58 +08:00
  • 5655f218ed add g_idx buffer.\nadd triton matmul utils for future support. John Smith 2023-04-02 21:29:06 +08:00
  • f3a25342e1 fix device_map bug when using lora_apply_dir John Smith 2023-03-31 19:44:36 +08:00
  • 00bf0a1e1b Update README.md John Smith 2023-03-31 14:17:35 +08:00
  • dd0efc721f Merge pull request #47 from winglian/better-gpt4all John Smith 2023-03-31 11:20:03 +08:00
  • 8791eaee9a fix gpt4all training to more closely match the released logic, other small fixes and optimizations Wing Lian 2023-03-30 19:08:35 -04:00
  • 878eada8dd add amp_wrapper for autocast support. John Smith 2023-03-30 19:57:19 +08:00
  • b3c91a5af5 Merge pull request #45 from winglian/fix-missing-bracket John Smith 2023-03-30 13:53:55 +08:00
  • e744aec8bf fix missing paren Wing Lian 2023-03-29 23:40:30 -04:00
  • 8db4633d84 Update README.md John Smith 2023-03-30 11:24:25 +08:00
  • 8a62560e6c add offload support John Smith 2023-03-30 11:21:21 +08:00
  • 32976f91c4 Merge pull request #42 from winglian/multigpu-fix John Smith 2023-03-30 00:03:27 +08:00
  • b7361da58a better multi-gpu support, support gpt4all training data Wing Lian 2023-03-29 11:21:47 -04:00
  • 0fdae9224c optimized groupsize backward for performance John Smith 2023-03-29 17:44:51 +08:00