Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
3,151 workflow runs
3,151 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

feat: add swanlab for experiment tracking and visualization. tests #1686: Pull request #6401 opened by Zeyi-Lin
December 20, 2024 03:29 Action required Zeyi-Lin:hiyouga/swanlab
Zeyi-Lin:hiyouga/swanlab
December 20, 2024 03:29 Action required
GLM模型如何实现train_on_prompt？ label_issue #1862: Issue #6400 opened by github-eliviate
December 20, 2024 02:58 11s
December 20, 2024 02:58 11s
Error Saving Model Due to Incorrect Relative Import label_issue #1861: Issue #6399 opened by maksimstw
December 19, 2024 20:48 11s
December 19, 2024 20:48 11s
Train a model from scratch label_issue #1860: Issue #6398 opened by nichellehouston
December 19, 2024 18:33 15s
December 19, 2024 18:33 15s
使用adma-mini进行Lora微调报错RuntimeError: shape '[-1, 655360]' is invalid for input of size 40960 label_issue #1859: Issue #6397 opened by TC10127
December 19, 2024 14:57 10s
December 19, 2024 14:57 10s
Add a loss_mask to control which outputs from the history are involved in the model's loss calculation. tests #1685: Pull request #6396 opened by summerwuxia
December 19, 2024 12:33 Action required summerwuxia:dev_sum
summerwuxia:dev_sum
December 19, 2024 12:33 Action required
Merge pull request #6395 from hiyouga/hiyouga/fix_genkwargs tests #1684: Commit c6e3c14 pushed by hiyouga
December 19, 2024 12:24 7m 42s main
main
December 19, 2024 12:24 7m 42s
[generate] fix generate kwargs tests #1683: Pull request #6395 opened by hiyouga
December 19, 2024 12:17 7m 18s hiyouga/fix_genkwargs
hiyouga/fix_genkwargs
December 19, 2024 12:17 7m 18s
感觉deepspeed zero3并没有实现模型切片 label_issue #1858: Issue #6394 opened by AIFFFENG
December 19, 2024 11:58 15s
December 19, 2024 11:58 15s
There might be an issue in mistral's chat template label_issue #1857: Issue #6393 opened by weirayao
December 19, 2024 11:31 15s
December 19, 2024 11:31 15s
ValueError: The following model_kwargs are not used by the model: ['skip_special_tokens'] label_issue #1855: Issue #6391 opened by paolovic
December 19, 2024 09:40 14s
December 19, 2024 09:40 14s
新手发问：SFT只有部分assistant的内容计算loss，该如何实现 label_issue #1854: Issue #6390 opened by ReycoLi
December 19, 2024 09:26 11s
December 19, 2024 09:26 11s
Merge pull request #6388 from hiyouga/hiyouga/shuffle_control tests #1682: Commit ffbb4db pushed by hiyouga
December 19, 2024 09:00 8m 20s main
main
December 19, 2024 09:00 8m 20s
[trainer] support disable shuffling tests #1681: Pull request #6388 opened by hiyouga
December 19, 2024 08:55 7m 28s hiyouga/shuffle_control
hiyouga/shuffle_control
December 19, 2024 08:55 7m 28s
How to reproduce the paper results? label_issue #1853: Issue #6387 opened by StiphyJay
December 19, 2024 07:46 10s
December 19, 2024 07:46 10s
LLaMA-Factory对话预期之外存在问题 label_issue #1852: Issue #6386 opened by 3237522375
December 19, 2024 07:31 11s
December 19, 2024 07:31 11s
如何把我训练的奖励模型放到ppo的工作管线里 label_issue #1851: Issue #6385 opened by chcoo
December 19, 2024 07:19 10s
December 19, 2024 07:19 10s
Merge pull request #6384 from hiyouga/hiyouga/fix_webui tests #1680: Commit 6ccd64e pushed by hiyouga
December 19, 2024 06:57 6m 45s main
main
December 19, 2024 06:57 6m 45s
[webui] fix webui args tests #1679: Pull request #6384 opened by hiyouga
December 19, 2024 06:48 7m 15s hiyouga/fix_webui
hiyouga/fix_webui
December 19, 2024 06:48 7m 15s
微调合并的模型 不能用transformers加载 label_issue #1850: Issue #6383 opened by flowermlh
December 19, 2024 03:18 11s
December 19, 2024 03:18 11s
求问，通过llama_factory打开了webui,怎样在webui里继续上次中断的训练？是把检查点路径设置为上一次中断后保存的checkpoint吗？ label_issue #1849: Issue #6382 opened by QinziLi-nanan
December 19, 2024 03:09 11s
December 19, 2024 03:09 11s
加载不上训练后的模型 label_issue #1848: Issue #6381 opened by dtiosd
December 18, 2024 09:54 12s
December 18, 2024 09:54 12s
LLaMA-Factory对话存在问题 label_issue #1847: Issue #6380 opened by 3237522375
December 18, 2024 09:16 10s
December 18, 2024 09:16 10s
Merge pull request #6379 from hiyouga/hiyouga/add_paligemma2 tests #1678: Commit 933647e pushed by hiyouga
December 18, 2024 09:03 8m 14s main
main
December 18, 2024 09:03 8m 14s
[model] add paligemma2 tests #1677: Pull request #6379 opened by hiyouga
December 18, 2024 08:58 7m 59s hiyouga/add_paligemma2
hiyouga/add_paligemma2
December 18, 2024 08:58 7m 59s