Commit Graph

  • 7272792f65 update wechat hiyouga 2024-08-27 12:55:23 +08:00
  • 4cc8e16595 add extra requires hiyouga 2024-08-27 12:52:12 +08:00
  • ca5a759f94 tiny fix hiyouga 2024-08-27 12:49:32 +08:00
  • be51e56a2e Merge pull request #5237 from marko1616/patch-1 hoshi-hiyouga 2024-08-27 12:24:43 +08:00
  • 3a9171e275 ruff pass. marko1616 2024-08-27 11:30:16 +08:00
  • bd0f3b4050 Update chat.py marko1616 2024-08-27 11:27:56 +08:00
  • 206a8364d4 support liger kernel hiyouga 2024-08-27 11:20:14 +08:00
  • 097d031066 Force re check. marko1616 2024-08-23 14:43:18 +08:00
  • 2674b42b59 Update chat.py marko1616 2024-08-22 12:24:34 +08:00
  • edf2e51bbc Update chat.py marko1616 2024-08-22 12:14:34 +08:00
  • 47877acc2a update npu base image MengqingCao 2024-08-21 09:12:38 +00:00
  • d111a324bc tiny fix hiyouga 2024-08-20 00:10:52 +08:00
  • 388f0a6e05 Merge pull request #5156 from YeQiuO/main hoshi-hiyouga 2024-08-20 00:09:03 +08:00
  • 8c13c02c55 Update template.py hoshi-hiyouga 2024-08-20 00:03:33 +08:00
  • a101fde917 Merge pull request #5163 from liu-zichen/fix_ppo_optim hoshi-hiyouga 2024-08-19 23:56:24 +08:00
  • 1f4373b6e5 Merge pull request #5185 from chenhuiyu/feature/add-sailorllm-template hoshi-hiyouga 2024-08-19 23:51:49 +08:00
  • 525747b472 Merge pull request #5188 from Zxilly/main hoshi-hiyouga 2024-08-19 23:51:39 +08:00
  • 472f12c985 Merge pull request #5193 from Ricardo-L-C/main hoshi-hiyouga 2024-08-19 23:40:59 +08:00
  • b681f24f43 Update template.py hoshi-hiyouga 2024-08-19 23:40:16 +08:00
  • fd02b089b6 update readme hiyouga 2024-08-19 23:32:04 +08:00
  • 57d4c4a4f8 _is_bf16_available judgment supports npu Ricardo 2024-08-16 02:58:22 +00:00
  • 3595d26846 fix: report correct device count for intel xpu Zxilly 2024-08-15 08:30:43 +00:00
  • 22a79c169d Add SailorLLM template Huiyu Chen 2024-08-15 15:10:14 +08:00
  • 75dfe259cf fix lr not change liu-zichen 2024-08-13 16:33:34 +08:00
  • 2e257d6af0 add tutorial and doc links codingma 2024-08-13 16:13:10 +08:00
  • e734222373 fix Llama-template's system prompt bug “Wzw” 2024-08-12 19:22:12 +08:00
  • 6a351b9912 update readme hiyouga 2024-08-10 10:17:35 +08:00
  • cfc04aa162 update readme hiyouga 2024-08-09 20:46:02 +08:00
  • 943c795318 add magpie ultra dataset hiyouga 2024-08-09 20:28:55 +08:00
  • 7fb61bad04 add qwen2 math models hiyouga 2024-08-09 20:20:35 +08:00
  • 47efcdb1dd update examples hiyouga 2024-08-09 20:13:46 +08:00
  • 59cbce1a46 add adam_mini to readme hiyouga 2024-08-09 20:02:03 +08:00
  • 7e755e9cac Merge pull request #5095 from relic-yuexi/feat-optimizer hoshi-hiyouga 2024-08-09 19:51:33 +08:00
  • 9d1e2c3c1f update scripts hiyouga 2024-08-09 19:16:23 +08:00
  • 5af32ce705 follow #5115 hiyouga 2024-08-09 18:03:00 +08:00
  • 4e8861e653 Merge pull request #5115 from YeQiuO/main hoshi-hiyouga 2024-08-09 17:58:27 +08:00
  • d4d7ffb17c Merge pull request #5072 from relic-yuexi/main hoshi-hiyouga 2024-08-09 16:35:21 +08:00
  • 46f834ec75 Update template.py hoshi-hiyouga 2024-08-09 16:27:42 +08:00
  • 6ec64a7e56 mask_history args verify valid “Wzw” 2024-08-08 10:12:01 +08:00
  • d71446e387 fix mask_history tiny bug “Wzw” 2024-08-08 10:09:33 +08:00
  • eada49e56b fix eval_dataset in example codingma 2024-08-07 18:24:19 +08:00
  • 8f42d7df56 feat: add support for adammini moontidef 2024-08-07 10:08:22 +08:00
  • 33a90b9026 fix: rename optimzer to optimizer moontidef 2024-08-07 10:05:01 +08:00
  • 710902b0d0 Merge branch 'hiyouga:main' into main moontidef 2024-08-06 00:18:45 +08:00
  • 7b4f5d3b21 fix: fix the deepseekcoder template to avoid repeat problem moontidef 2024-08-05 23:55:45 +08:00
  • 13093963b1 fix #5048 hiyouga 2024-08-05 23:48:19 +08:00
  • 2e477e7458 Merge pull request #5037 from codemayq/feature-gemma-2-2b hoshi-hiyouga 2024-08-05 23:27:37 +08:00
  • 4b6252151e support gemma-2-2b codingma 2024-08-01 13:45:48 +08:00
  • f3765d1996 Merge pull request #5010 from Eruly/main hoshi-hiyouga 2024-07-30 01:55:54 +08:00
  • 1f5cdd66b7 Merge pull request #4996 from LDLINGLINGLING/main hoshi-hiyouga 2024-07-30 01:55:30 +08:00
  • 5b0ddbb835 Update README_zh.md hoshi-hiyouga 2024-07-30 01:55:13 +08:00
  • 4f92b56f06 Update README.md hoshi-hiyouga 2024-07-30 01:53:19 +08:00
  • a1f6ff92be Update README.md hoshi-hiyouga 2024-07-30 01:52:35 +08:00
  • ef98e91618 Merge pull request #4995 from codemayq/fix-pissa hoshi-hiyouga 2024-07-30 01:47:25 +08:00
  • 9fdf800750 Add Korean web UI (llamafactory-cli webui) eruly 2024-07-29 13:47:13 +00:00
  • 32c698e4c2 增加了MiniCPM在页面首页的支持列表,MiniCPM官方github也放了LLama_factory的友情链接 liudan 2024-07-29 10:58:28 +08:00
  • 75e80fa820 fix pissa save codingma 2024-07-29 10:44:34 +08:00
  • f8329bc632 tiny fix hiyouga 2024-07-26 11:51:00 +08:00
  • 9f74d36ba4 Merge pull request #4892 from piamo/main hoshi-hiyouga 2024-07-26 11:49:34 +08:00
  • fc2435f135 Merge pull request #4950 from liuwwang/main and fi hoshi-hiyouga 2024-07-26 11:48:56 +08:00
  • 0636519ba3 Merge pull request #4970 from HardAndHeavy/add-rocm hoshi-hiyouga 2024-07-26 11:41:23 +08:00
  • 573bf03a6f Update README_zh.md hoshi-hiyouga 2024-07-26 11:30:57 +08:00
  • 9e529be4e7 Update README.md hoshi-hiyouga 2024-07-26 11:29:28 +08:00
  • 7af4ffa6cc Update README.md hoshi-hiyouga 2024-07-26 11:29:09 +08:00
  • 5b67ccd1c6 Add ROCm support HardAndHeavy 2024-07-25 21:29:28 +03:00
  • 5166dbbcd3 Added the reference address for TRL PPO details. khazic 2024-07-25 09:03:21 +08:00
  • 21adb09730 fix #4959 hiyouga 2024-07-24 23:44:00 +08:00
  • 28b5f656db update webui hiyouga 2024-07-24 21:11:51 +08:00
  • 68ee2d512f Update README_zh.md hoshi-hiyouga 2024-07-24 21:08:42 +08:00
  • a5f7e0efc6 Update README.md hoshi-hiyouga 2024-07-24 21:07:14 +08:00
  • 211038584a tiny fix hiyouga 2024-07-24 18:33:39 +08:00
  • ff5ba97970 fix #4928 hiyouga 2024-07-24 17:00:29 +08:00
  • 27f2c3cae1 fix #4925 hiyouga 2024-07-24 16:56:58 +08:00
  • 48f0819327 fix #4944 hiyouga 2024-07-24 16:42:51 +08:00
  • 5c6d88e91c add mistral nemo model hiyouga 2024-07-24 16:25:53 +08:00
  • 0a04d9470f add llama3.1 hiyouga 2024-07-24 16:20:11 +08:00
  • f0408c0dde fix: Repair the issue where quantization failed after merging the adapter. Former-commit-id: 8109561b7f577d448f8bca7e569f7f443cf6bb52 Liuww 2024-07-24 14:31:29 +08:00
  • a041f4a111 tiny fix hiyouga 2024-07-22 21:10:15 +08:00
  • cdf9dae53e fix #4917 hoshi-hiyouga 2024-07-22 11:28:31 +08:00
  • 1917f431f5 tiny fix hiyouga 2024-07-22 00:06:03 +08:00
  • a770afbff2 fix flashattn + packing hiyouga 2024-07-21 17:07:45 +08:00
  • b1a5bf025b update deepseek template huangpan.foo 2024-07-19 15:02:54 +08:00
  • adff3e5050 set dev version hiyouga 2024-07-19 02:01:46 +08:00
  • 0e88c5754f update parser v0.8.3 hiyouga 2024-07-19 01:36:39 +08:00
  • 3fff875f99 release v0.8.3 hiyouga 2024-07-19 01:21:18 +08:00
  • e2d9ab3591 fix test hiyouga 2024-07-19 01:17:37 +08:00
  • 3db5cf44ea fix unittest hiyouga 2024-07-19 01:10:30 +08:00
  • 994b9089e9 add unittest hiyouga 2024-07-19 01:06:27 +08:00
  • 4c1513a845 follow #4878 fix #4684 hiyouga 2024-07-18 22:06:12 +08:00
  • 86e009b504 Merge pull request #4878 from ly863/main hoshi-hiyouga 2024-07-18 22:03:41 +08:00
  • c1e1918db1 仅仅训练最后一轮对话 Shiyu Zhang 2024-07-18 15:30:25 +08:00
  • 341225a405 fix metrics #4786 hiyouga 2024-07-17 00:47:00 +08:00
  • 8c93921952 support batch_eval_metrics, fix #4826 hiyouga 2024-07-17 00:33:00 +08:00
  • 45367105fc tiny fix hiyouga 2024-07-15 23:09:50 +08:00
  • df71359069 Merge pull request #4822 from codemayq/test-ci hoshi-hiyouga 2024-07-15 23:07:55 +08:00
  • a03d14a9a6 Update test_template.py hoshi-hiyouga 2024-07-15 23:04:39 +08:00
  • 41d7ca395e Update test_template.py hoshi-hiyouga 2024-07-15 23:00:27 +08:00
  • 757573bec1 Merge pull request #4821 from codemayq/feature-eval-split hoshi-hiyouga 2024-07-15 22:59:44 +08:00
  • 16d655b119 Update llama3_lora_eval.yaml hoshi-hiyouga 2024-07-15 22:55:12 +08:00
  • f6483de197 Update test_template.py hoshi-hiyouga 2024-07-15 22:55:05 +08:00