Commit Graph

165 Commits

Author SHA1 Message Date
Colin 0458e7303c Remove attention_mask 2024-01-20 18:08:20 +08:00
Colin cd50c10e8c Move readme to charglm. 2024-01-20 00:11:12 +08:00
Colin e7ba788982 Delete docs. 2024-01-20 00:10:27 +08:00
colin 69154a4777 删除 doc/主观意识生成对话.md 2024-01-19 18:22:50 +08:00
colin fd0b0c63ba 删除 chatglm/graph.md 2024-01-19 18:22:39 +08:00
Colin f96bcc799c Refine model of qwen for long sequence in eval. 2024-01-19 14:54:48 +08:00
Colin 45c2f532ff Add mem_tracker in tools. 2024-01-19 14:52:28 +08:00
Colin 3233616aac Delete kv cache of qwen. 2024-01-18 20:23:21 +08:00
Colin 0a78627e48 Add doc 2024-01-17 22:56:30 +08:00
Colin 90fbc2642e Refine modeling and demo. 2024-01-14 17:21:14 +08:00
Colin 332d27cc05 Delete unused files. 2024-01-14 15:42:46 +08:00
Colin fb276cdeea Add test markdown for document. 2024-01-14 14:28:45 +08:00
Colin d13f7e6c57 Format model of qwen. 2024-01-13 17:16:43 +08:00
Colin 5cf6e8b013 Refine qwen model. 2024-01-13 16:50:25 +08:00
Colin 9386d044b6 Update tools of show. 2024-01-13 16:48:56 +08:00
Colin 063f722177 Refine model of qwen. 2024-01-11 07:00:18 +00:00
Colin 7d7b4381f8 Update qwen model. 2024-01-10 13:16:54 +00:00
Colin 245d251663 Refine chat output format. 2024-01-10 11:35:46 +00:00
Colin 1b8007e1c3 Refine train. 2024-01-10 05:22:26 +00:00
Colin 69cb525ab0 Refine model of qwen. 2024-01-07 22:49:21 +08:00
Colin 94ecf0f561 Refine model of qwen. 2024-01-07 22:36:55 +08:00
Colin 4c0991a409 Re format qwen. 2024-01-07 21:54:37 +08:00
Colin aa2d3b96c4 Delete unused files. 2024-01-07 21:43:02 +08:00
Colin 82ac3e4863 Refine model of qwen. 2024-01-07 17:50:58 +08:00
Colin 3f8ea9db07 Remote return_dict_in_generate 2024-01-07 17:32:24 +08:00
Colin a8f2fbbff5 Remote return_dict config. Remove unuse files. 2024-01-07 17:28:15 +08:00
Colin 90cb0fe236 Refine model of qwen. 2024-01-07 16:53:53 +08:00
Colin 611396b656 Format qwen model. 2024-01-07 16:23:04 +08:00
Colin 255a2ff71c Update qwen model. 2024-01-07 16:22:41 +08:00
Colin f6538c1111 Update qwen model add generator and sample. 2024-01-07 16:15:27 +08:00
Colin 08f7b75efe Add train resnet test. 2024-01-07 15:09:45 +08:00
Colin 467c78d83d Update and try seqgpt 2024-01-07 15:06:39 +08:00
Colin 0dd2f2bab4 add seqgpt and prompt_clue 2024-01-06 21:05:39 +08:00
Colin 65578680cf Add prompt_clue. 2024-01-05 20:33:01 +08:00
Colin 55fed4bc5a Update qwen demo.py 2024-01-05 11:49:35 +08:00
Colin 8adae2130c Update chatglm train. 2024-01-04 19:56:30 +08:00
Colin 9deb809a88 Update finetune 2024-01-04 19:12:28 +08:00
Colin ec72ee1141 Add finetune 2024-01-04 17:36:41 +08:00
Colin 9b90c607e0 Add qwen files. 2024-01-03 21:03:27 +08:00
Colin 3a4e99f7e3 Add qwen and refine folders. 2024-01-03 20:26:26 +08:00
Colin 0fa38b7815 Update graph.md. 2024-01-01 22:45:16 +08:00
Colin b3ef30aa1a Format code. 2024-01-01 10:20:56 +08:00
colin bde8f71a7f 更新 Readme.md 2023-12-31 17:42:21 +08:00
colin 1579e0b8f2 更新 Readme.md 2023-12-31 15:26:29 +08:00
colin d9b64e4025 更新 Readme.md 2023-12-31 15:26:02 +08:00
Colin dff2b9231f Update. 2023-12-29 20:39:40 +08:00
Colin 3db6e2c25b Update. 2023-12-29 19:55:53 +08:00
Colin b3df9e423c Update. 2023-12-27 19:58:52 +08:00
Colin 0cee40dbb0 Add output_layer_weight dump. 2023-12-26 18:59:28 +08:00
Colin 235f65aa19 Update readme. 2023-12-26 18:14:11 +08:00