Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 2f704b93c9 add test result main John Smith 2023-04-26 18:02:43 +0800
• 73f51188bf Update readme John Smith 2023-04-26 17:53:26 +0800
• 97804534b9 fix reference John Smith 2023-04-26 17:29:29 +0800
• 8e5cf08479 fix dependency John Smith 2023-04-26 17:17:59 +0800
• 42ef3484a9 fix _SentinelTokenStoppingCriteria John Smith 2023-04-26 14:38:57 +0800
• d6791790ed fix bug John Smith 2023-04-26 13:13:54 +0800
• 1abdc99675 add server John Smith 2023-04-26 12:50:36 +0800
• 633c28fd25 add quant attn v1 support John Smith 2023-04-25 12:28:45 +0800
• f9c94f27cc fix bug John Smith 2023-04-25 09:21:15 +0800
• b5af5c00e1 optimize lora compute John Smith 2023-04-23 20:00:28 +0800
• 82bbea2729 optimized matmul for v2 model John Smith 2023-04-22 23:01:39 +0800
• 9fe5ab3642 fix bug John Smith 2023-04-22 17:23:24 +0800
• 4e42965c0d Merge branch 'main' of github.com:johnsmith0031/alpaca_lora_4bit John Smith 2023-04-22 16:35:37 +0800
• eb442494d1 optimize mem usage John Smith 2023-04-22 16:35:18 +0800
• 51bf103269
  Update README.md John Smith 2023-04-22 16:09:38 +0800
• 33a76b00ca
  Update README.md John Smith 2023-04-22 15:58:06 +0800
• 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 +0800
• 35caccd376 add assert John Smith 2023-04-21 10:24:58 +0800
• 1a0c63edaf
  Update README.md John Smith 2023-04-20 10:04:13 +0800
• a0a0962de7
  Update README.md John Smith 2023-04-20 09:57:18 +0800
• 3b18aa1cc6 fix bug and remove bnb John Smith 2023-04-20 09:51:57 +0800
• 90e628121a fix continue training for this version John Smith 2023-04-17 14:16:05 +0800
• e64ff9facd fix bug John Smith 2023-04-17 13:42:50 +0800
• 7a71b0dd12 fix bug when loading old lora model John Smith 2023-04-17 12:16:21 +0800
• 6739f529f5
  Merge pull request #79 from wesleysanjose/main John Smith 2023-04-15 00:53:59 +0800
• b8e2588fbf
  Fix Dockerfile for No module named 'monkeypatch' wesleysanjose 2023-04-14 01:27:44 -0700
• fb7665726e
  Update requirements.txt John Smith 2023-04-13 14:44:59 +0800
• 9c3058c1de fix bug John Smith 2023-04-13 11:34:53 +0800
• 76d7963dff fix bug John Smith 2023-04-13 10:36:57 +0800
• 6aab31bd73 update reference John Smith 2023-04-13 10:35:10 +0800
• 5ff11b5bf2
  Merge pull request #77 from winglian/upstream-peft John Smith 2023-04-13 10:25:05 +0800
• f4b1dc19ab addtional fix Wing Lian 2023-04-12 06:54:23 -0400
• 17e6a1585f
  Update README.md John Smith 2023-04-12 13:09:48 +0800
• e946f830d4 minor fix John Smith 2023-04-12 13:06:30 +0800
• 4261bd8070 add xformers support John Smith 2023-04-12 12:59:44 +0800
• 7871baf311 fix bug on v1 finetune John Smith 2023-04-11 19:15:56 +0800
• 7762459f1f
  Merge pull request #74 from andybarry/readme_fix John Smith 2023-04-10 21:38:06 +0800
• 68e1b35660
  Merge pull request #73 from dnouri/fix-monkeypatch-v1 John Smith 2023-04-10 21:37:27 +0800
• e590407c5f Fix readme typo. Andy Barry 2023-04-10 08:56:05 -0400
• ee7d94a1f3 Bugfix in custom_monkey_patch for v1 models Daniel Nouri 2023-04-10 12:41:16 +0200
• 5d3267d80d add v1 model as default in custom monkey patch John Smith 2023-04-10 09:33:41 +0800
• c2b33bacc9 use monkey patch instead of forked peft Wing Lian 2023-04-09 11:40:58 -0400
• f185b90c3e
  Update README.md John Smith 2023-04-09 12:50:49 +0800
• 4c18a56fc0 fix bug John Smith 2023-04-09 12:44:50 +0800
• 8cf3bd4086 add g_idx support on cuda backend John Smith 2023-04-09 12:26:22 +0800
• b73f4e5e64
  Merge pull request #64 from andybarry/readme_fix John Smith 2023-04-09 11:15:23 +0800
• b5d49cb9b1 Fix URL in readme. Andy Barry 2023-04-08 12:38:45 -0400
• 132c67be0d
  Fix bug John Smith 2023-04-08 23:58:30 +0800
• 56e5bf2854
  Merge pull request #63 from andybarry/dockerfile John Smith 2023-04-08 15:48:27 +0800
• a93cf1264a Add timing on readme, remove useless line in dockerfile. Andy Barry 2023-04-08 01:54:29 -0400
• 191d92c940 Clean up diff Andy Barry 2023-04-08 01:27:56 -0400
• 31614fc2c4 Move 7bn changes into dockerfile. Andy Barry 2023-04-08 01:21:17 -0400
• 2e5aaf6dd6 Merge readmes. Andy Barry 2023-04-08 01:14:54 -0400
• e854f5d111 Fix after merge. Andy Barry 2023-04-08 00:53:28 -0400
• 8435b2c7f2 Merge branch 'main' of https://github.com/johnsmith0031/alpaca_lora_4bit Andy Barry 2023-04-07 22:02:54 -0400
• f91d4cbb59
  Update README.md John Smith 2023-04-07 16:10:36 +0800
• b01b10eb4d Colorized output John Smith 2023-04-07 15:58:38 +0800
• 32904da1ff fix bug on triton matmul John Smith 2023-04-07 15:50:55 +0800
• dba3773b30 add triton backend support for v2 model John Smith 2023-04-07 15:34:06 +0800
• 9351f49542 merge pull request in new branch John Smith 2023-04-07 10:40:24 +0800
• 85e9cf004a
  Merge pull request #59 from yamashi/main John Smith 2023-04-07 10:05:18 +0800
• c5aa7fb695
  Update finetune.py yamashi 2023-04-07 00:43:36 +0200
• 95cd390d25
  Update Finetune4bConfig.py yamashi 2023-04-07 00:43:15 +0200
• 778035152d
  Update arg_parser.py yamashi 2023-04-07 00:42:34 +0200
• 2bf5d42f28
  Add position_ids to flash attention yamashi 2023-04-06 17:46:15 +0200
• 7770e76c9c
  Fix args of flash attention yamashi 2023-04-06 17:32:01 +0200
• 30bf938d03
  Update requirements.txt yamashi 2023-04-06 13:50:25 +0200
• 7b18b39dd8
  Create llama_flash_attn_monkey_patch.py yamashi 2023-04-06 13:49:36 +0200
• 3ea18575c7
  Use flash attention monkeypatch yamashi 2023-04-06 13:49:12 +0200
• 8020b3ec3b
  Update README.md John Smith 2023-04-06 13:57:32 +0800
• 9a02a88fb8 add patch for encode function to remove eos token at the beginning of left side John Smith 2023-04-06 12:56:27 +0800
• 3a95ad894b
  Update README.md Andy Barry 2023-04-06 00:53:57 -0400
• 1b8b6e193c Merge branch 'main' of github.com:andybarry/alpaca_lora_4bit_docker Andy Barry 2023-04-06 00:31:29 -0400
• 3076eaf4aa Add gif. Andy Barry 2023-04-06 00:30:28 -0400
• 0a51b6b0ee
  Update README.md Andy Barry 2023-04-06 00:20:30 -0400
• 6130b9bd0f
  Update README.md Andy Barry 2023-04-06 00:06:29 -0400
• 0f25304184
  Update README.md Andy Barry 2023-04-06 00:06:05 -0400
• 242fc92e54 Fix url Andy Barry 2023-04-05 23:38:28 -0400
• fa966018f4 Fix docker run command. Andy Barry 2023-04-05 23:38:00 -0400
• 1af4023883 Fix some issues. Andy Barry 2023-04-05 23:29:10 -0400
• 417eba372a Add dockerfile and change some numbers to use 7bn model. Andy Barry 2023-04-05 23:13:35 -0400
• 085d9556f9 fix bug John Smith 2023-04-06 10:46:42 +0800
• c991e2a091
  Delete triton_test.py Andrey Glushenkov 2023-04-06 02:39:40 +0300
• 0d271d5d90
  Add files via upload Andrey Glushenkov 2023-04-06 02:38:06 +0300
• 4a2d23aa29
  Delete autograd_4bit.py Andrey Glushenkov 2023-04-06 02:31:06 +0300
• f20570343f
  GPTQv2 support Andrey Glushenkov 2023-04-06 02:29:36 +0300
• 86387a0a35 update multi gpu support in finetune.py John Smith 2023-04-03 23:55:58 +0800
• 5655f218ed add g_idx buffer.\nadd triton matmul utils for future support. John Smith 2023-04-02 21:29:06 +0800
• f3a25342e1 fix device_map bug when using lora_apply_dir John Smith 2023-03-31 19:44:36 +0800
• 00bf0a1e1b
  Update README.md John Smith 2023-03-31 14:17:35 +0800
• dd0efc721f
  Merge pull request #47 from winglian/better-gpt4all John Smith 2023-03-31 11:20:03 +0800
• 8791eaee9a fix gpt4all training to more closely match the released logic, other small fixes and optimizations Wing Lian 2023-03-30 19:08:35 -0400
• 878eada8dd add amp_wrapper for autocast support. John Smith 2023-03-30 19:57:19 +0800
• b3c91a5af5
  Merge pull request #45 from winglian/fix-missing-bracket John Smith 2023-03-30 13:53:55 +0800
• e744aec8bf fix missing paren Wing Lian 2023-03-29 23:40:30 -0400
• 8db4633d84
  Update README.md John Smith 2023-03-30 11:24:25 +0800
• 8a62560e6c add offload support John Smith 2023-03-30 11:21:21 +0800
• 32976f91c4
  Merge pull request #42 from winglian/multigpu-fix John Smith 2023-03-30 00:03:27 +0800
• b7361da58a better multi-gpu support, support gpt4all training data Wing Lian 2023-03-29 11:21:47 -0400
• 0fdae9224c optimized groupsize backward for performance John Smith 2023-03-29 17:44:51 +0800