Commit Graph

  • 8330cbb036 Add meaning dataset. Colin 2024-03-13 19:41:02 +0800
  • c094afb0f9 Add tensorboard event out. Colin 2024-03-09 16:55:03 +0800
  • f1394d5974 Refine code. Colin 2024-03-08 20:46:42 +0800
  • 601c7f6510 Retest wit. Colin 2024-03-07 16:30:37 +0800
  • a70d12d04d Rename train file. Colin 2024-03-05 22:09:58 +0800
  • 9ef3e92b23 Try model train. Colin 2024-03-05 22:09:28 +0800
  • 11fc8f1d39 Refine label used. Colin 2024-03-05 22:08:37 +0800
  • fdc8c657b3 Add accurancy in loss. Colin 2024-03-05 19:30:15 +0800
  • cf726a5b9f Add loss and logger code. Colin 2024-03-05 15:54:03 +0800
  • 9e8e92ae25 Update trainer to custom data. Colin 2024-03-04 21:41:46 +0800
  • 1622bf3054 add mnbvc dataset . Colin 2024-03-03 23:35:40 +0800
  • 8120be66a6 sperate train and val dataset. Colin 2024-02-26 23:59:00 +0800
  • d1906629ab Enable wit train on cutome dataset and loss down. Colin 2024-02-26 22:42:50 +0800
  • 1ef3e419cb Add custom dataset support. Colin 2024-02-26 00:31:47 +0800
  • e5f97af291 Add wit train support. Colin 2024-02-25 20:20:32 +0800
  • fc071dce70 Remove no use tiktoken. Colin 2024-02-21 21:11:15 +0800
  • fe13f12327 Add wit. Colin 2024-02-06 14:08:45 +0800
  • 6366b52fef Add reaserch sile resault. Colin 2024-02-04 23:48:51 +0800
  • 9d5d590b09 Add dataset and wit. Colin 2024-02-04 23:48:24 +0800
  • b7c27af6c8 Add research_token to dump token relationship in attention layer0. Colin 2024-01-29 00:12:08 +0800
  • 185278f3a9 Update research_attention dump without sum. Colin 2024-01-28 17:55:08 +0800
  • 3f296ccdb2 Update research. Colin 2024-01-26 20:35:25 +0800
  • bba27e3444 Refine prepareInput. Colin 2024-01-25 18:05:08 +0800
  • 19491d1f4a Refine model of qwen. Colin 2024-01-24 21:22:03 +0800
  • 11af10e710 Refine research_attention and forward model. Colin 2024-01-23 13:13:21 +0800
  • 1811b9611a Refine research_attention. Colin 2024-01-22 20:57:27 +0800
  • 5dbac40925 Refien. Colin 2024-01-21 22:43:16 +0800
  • 17a2df2e6f Update show and q@k dump. Colin 2024-01-21 20:50:36 +0800
  • ae6ea67bbe Refine qwen/research_attention.py. Colin 2024-01-21 17:54:05 +0800
  • dab1c94bc6 Refine qwen to module fomater. Colin 2024-01-21 16:46:00 +0800
  • 9d28280cb1 Refine model of qwen and add runner. Colin 2024-01-21 12:45:56 +0800
  • 7c047f0b32 Refine model of qwen. Colin 2024-01-21 02:33:55 +0800
  • 40ae899515 Refine model of qwen. Colin 2024-01-20 20:47:26 +0800
  • 4d493014ba Refine model of qwen. Colin 2024-01-20 20:20:18 +0800
  • 12dcbec718 PreTrainedModel to mm.Module Colin 2024-01-20 20:04:45 +0800
  • 0458e7303c Remove attention_mask Colin 2024-01-20 18:08:20 +0800
  • cd50c10e8c Move readme to charglm. Colin 2024-01-20 00:11:12 +0800
  • e7ba788982 Delete docs. Colin 2024-01-20 00:10:27 +0800
  • 69154a4777 删除 doc/主观意识生成对话.md colin 2024-01-19 18:22:50 +0800
  • fd0b0c63ba 删除 chatglm/graph.md colin 2024-01-19 18:22:39 +0800
  • 7cf19b15cf Add image dump of query matmul key query_matmul_key Colin 2024-01-19 16:32:38 +0800
  • f96bcc799c Refine model of qwen for long sequence in eval. Colin 2024-01-19 14:54:48 +0800
  • 45c2f532ff Add mem_tracker in tools. Colin 2024-01-19 14:52:28 +0800
  • 3233616aac Delete kv cache of qwen. Colin 2024-01-18 20:23:21 +0800
  • 0a78627e48 Add doc Colin 2024-01-17 22:50:39 +0800
  • 90fbc2642e Refine modeling and demo. Colin 2024-01-14 17:21:14 +0800
  • 332d27cc05 Delete unused files. Colin 2024-01-14 15:42:46 +0800
  • fb276cdeea Add test markdown for document. Colin 2024-01-14 14:28:45 +0800
  • d13f7e6c57 Format model of qwen. Colin 2024-01-13 17:16:43 +0800
  • 5cf6e8b013 Refine qwen model. Colin 2024-01-13 16:50:25 +0800
  • 9386d044b6 Update tools of show. Colin 2024-01-13 16:48:56 +0800
  • 063f722177 Refine model of qwen. Colin 2024-01-11 07:00:18 +0000
  • 7d7b4381f8 Update qwen model. Colin 2024-01-10 13:16:54 +0000
  • 245d251663 Refine chat output format. Colin 2024-01-10 11:35:46 +0000
  • 1b8007e1c3 Refine train. Colin 2024-01-10 05:22:26 +0000
  • 69cb525ab0 Refine model of qwen. Colin 2024-01-07 22:49:21 +0800
  • 94ecf0f561 Refine model of qwen. Colin 2024-01-07 22:36:55 +0800
  • 4c0991a409 Re format qwen. Colin 2024-01-07 21:54:37 +0800
  • aa2d3b96c4 Delete unused files. Colin 2024-01-07 21:43:02 +0800
  • 82ac3e4863 Refine model of qwen. Colin 2024-01-07 17:50:58 +0800
  • 3f8ea9db07 Remote return_dict_in_generate Colin 2024-01-07 17:32:24 +0800
  • a8f2fbbff5 Remote return_dict config. Remove unuse files. Colin 2024-01-07 17:28:15 +0800
  • 90cb0fe236 Refine model of qwen. Colin 2024-01-07 16:53:53 +0800
  • 611396b656 Format qwen model. Colin 2024-01-07 16:23:04 +0800
  • 255a2ff71c Update qwen model. Colin 2024-01-07 16:22:41 +0800
  • f6538c1111 Update qwen model add generator and sample. Colin 2024-01-07 16:15:27 +0800
  • 08f7b75efe Add train resnet test. Colin 2024-01-07 15:09:45 +0800
  • 467c78d83d Update and try seqgpt Colin 2024-01-07 15:06:39 +0800
  • 0dd2f2bab4 add seqgpt and prompt_clue Colin 2024-01-06 21:05:39 +0800
  • 65578680cf Add prompt_clue. Colin 2024-01-05 20:33:01 +0800
  • 55fed4bc5a Update qwen demo.py Colin 2024-01-05 11:49:35 +0800
  • 8adae2130c Update chatglm train. Colin 2024-01-04 19:56:30 +0800
  • 9deb809a88 Update finetune Colin 2024-01-04 19:12:28 +0800
  • ec72ee1141 Add finetune Colin 2024-01-04 17:36:41 +0800
  • 9b90c607e0 Add qwen files. Colin 2024-01-03 21:03:27 +0800
  • 3a4e99f7e3 Add qwen and refine folders. Colin 2024-01-03 20:26:26 +0800
  • 0fa38b7815 Update graph.md. Colin 2024-01-01 22:45:16 +0800
  • b3ef30aa1a Format code. Colin 2024-01-01 10:20:04 +0800
  • bde8f71a7f 更新 Readme.md colin 2023-12-31 17:42:21 +0800
  • 1579e0b8f2 更新 Readme.md colin 2023-12-31 15:26:29 +0800
  • d9b64e4025 更新 Readme.md colin 2023-12-31 15:26:02 +0800
  • dff2b9231f Update. Colin 2023-12-29 20:39:40 +0800
  • 3db6e2c25b Update. Colin 2023-12-29 19:55:53 +0800
  • b3df9e423c Update. Colin 2023-12-27 19:58:52 +0800
  • 0cee40dbb0 Add output_layer_weight dump. Colin 2023-12-26 18:59:28 +0800
  • 235f65aa19 Update readme. Colin 2023-12-26 18:14:11 +0800
  • 29fb562aea Update more dump. Colin 2023-12-26 14:08:02 +0800
  • 72c13cde02 Update show and output tokens image. Colin 2023-12-25 22:53:53 +0800
  • 0bc7bc90b1 Update code. Colin 2023-12-25 17:26:19 +0800
  • fa7078b72d Update code. Colin 2023-12-25 16:22:45 +0800
  • ebe48f8efc Update readme. Colin 2023-12-22 20:01:09 +0800
  • 9c19c9f285 Add model config json files. Colin 2023-12-22 19:14:22 +0800
  • 72787b9268 Refien sample code. Colin 2023-12-22 18:57:16 +0800
  • 10268c4414 Update code. Colin 2023-12-22 18:01:57 +0800
  • 185caa12e9 Refine model. Colin 2023-12-22 12:59:53 +0800
  • 84938e565e Refien model code. Colin 2023-12-22 11:39:06 +0800
  • 539392c843 Add auto2d. Colin 2023-12-21 21:20:49 +0800
  • bfc3fb6706 Refine. Colin 2023-12-21 20:52:19 +0800
  • c462129ba6 Refine Code. Colin 2023-12-21 20:50:10 +0800
  • 68417fdc12 Add dump tool. Colin 2023-12-21 19:52:19 +0800