Commit Graph

140 Commits

Author SHA1 Message Date
deep1 e4c04daadf git clone script working 2023-04-22 18:42:01 +08:00
deep1 ba547ccb70 update download script 2023-04-22 16:03:20 +08:00
wassname 3410c9cad0 tidy 2023-04-22 07:50:21 +00:00
wassname d149f12704 readme 2023-04-22 00:27:30 +00:00
wassname 830c8f2605 gitkeep 2023-04-22 00:26:42 +00:00
wassname 2e7bf22d4a misc 2023-04-22 00:24:57 +00:00
wassname 4155cbb641 delora and test works :) 2023-04-15 13:11:15 +00:00
wassname e6338b5b26 rm int4 2023-04-15 06:37:43 +00:00
wassname c520ad64ba trying to load int4 2023-04-15 06:23:33 +00:00
wassname 3a8c7f3a5b convert running, test working 2023-04-10 19:47:53 +08:00
wassname 039af1a0db readme 2023-04-10 16:21:01 +08:00
wassname e6f36838fe readme 2023-04-10 16:17:13 +08:00
wassname 6e6c8f8e7a init 2023-04-10 16:15:52 +08:00
John Smith 5d3267d80d add v1 model as default in custom monkey patch 2023-04-10 09:33:41 +08:00
John Smith f185b90c3e Update README.md 2023-04-09 12:50:49 +08:00
John Smith 4c18a56fc0 fix bug 2023-04-09 12:44:50 +08:00
John Smith 8cf3bd4086 add g_idx support on cuda backend 2023-04-09 12:26:22 +08:00
John Smith b73f4e5e64 Merge pull request #64 from andybarry/readme_fix
Fix URL in readme
2023-04-09 11:15:23 +08:00
Andy Barry b5d49cb9b1 Fix URL in readme. 2023-04-08 12:38:45 -04:00
John Smith 132c67be0d Fix bug 2023-04-08 23:58:30 +08:00
John Smith 56e5bf2854 Merge pull request #63 from andybarry/dockerfile
Add a Dockerfile and readme changes for quick start
2023-04-08 15:48:27 +08:00
Andy Barry a93cf1264a Add timing on readme, remove useless line in dockerfile. 2023-04-08 01:54:29 -04:00
Andy Barry 191d92c940 Clean up diff 2023-04-08 01:27:56 -04:00
Andy Barry 31614fc2c4 Move 7bn changes into dockerfile. 2023-04-08 01:21:17 -04:00
Andy Barry 2e5aaf6dd6 Merge readmes. 2023-04-08 01:14:54 -04:00
Andy Barry e854f5d111 Fix after merge. 2023-04-08 00:53:28 -04:00
Andy Barry 8435b2c7f2 Merge branch 'main' of https://github.com/johnsmith0031/alpaca_lora_4bit 2023-04-07 22:02:54 -04:00
John Smith f91d4cbb59 Update README.md 2023-04-07 16:10:36 +08:00
John Smith b01b10eb4d Colorized output 2023-04-07 15:58:38 +08:00
John Smith 32904da1ff fix bug on triton matmul 2023-04-07 15:50:55 +08:00
John Smith dba3773b30 add triton backend support for v2 model 2023-04-07 15:34:06 +08:00
John Smith 9351f49542 merge pull request in new branch 2023-04-07 10:40:24 +08:00
John Smith 85e9cf004a Merge pull request #59 from yamashi/main
Add flash attention
2023-04-07 10:05:18 +08:00
yamashi c5aa7fb695 Update finetune.py 2023-04-07 00:43:36 +02:00
yamashi 95cd390d25 Update Finetune4bConfig.py 2023-04-07 00:43:15 +02:00
yamashi 778035152d Update arg_parser.py 2023-04-07 00:42:34 +02:00
yamashi 2bf5d42f28 Add position_ids to flash attention 2023-04-06 17:46:15 +02:00
yamashi 7770e76c9c Fix args of flash attention 2023-04-06 17:32:01 +02:00
yamashi 30bf938d03 Update requirements.txt 2023-04-06 13:50:25 +02:00
yamashi 7b18b39dd8 Create llama_flash_attn_monkey_patch.py 2023-04-06 13:49:36 +02:00
yamashi 3ea18575c7 Use flash attention monkeypatch 2023-04-06 13:49:12 +02:00
John Smith 8020b3ec3b Update README.md 2023-04-06 13:57:32 +08:00
John Smith 9a02a88fb8 add patch for encode function to remove eos token at the beginning of left side 2023-04-06 12:56:27 +08:00
Andy Barry 3a95ad894b Update README.md 2023-04-06 00:53:57 -04:00
Andy Barry 1b8b6e193c Merge branch 'main' of github.com:andybarry/alpaca_lora_4bit_docker 2023-04-06 00:31:29 -04:00
Andy Barry 3076eaf4aa Add gif. 2023-04-06 00:30:28 -04:00
Andy Barry 0a51b6b0ee Update README.md 2023-04-06 00:20:30 -04:00
Andy Barry 6130b9bd0f Update README.md 2023-04-06 00:06:29 -04:00
Andy Barry 0f25304184 Update README.md 2023-04-06 00:06:05 -04:00
Andy Barry 242fc92e54 Fix url 2023-04-05 23:38:28 -04:00