Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,525 workflow runs
2,525 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

NPU训练支持的模型列表有哪些？ label_issue #1385: Issue #5779 opened by yangyang6666
October 22, 2024 09:30 11s
October 22, 2024 09:30 11s
DPO Logging Metrics label_issue #1384: Issue #5778 opened by jianhai0527
October 22, 2024 09:23 11s
October 22, 2024 09:23 11s
您好，关于数据集预处理中的processor参数问题 label_issue #1383: Issue #5777 opened by judyself
October 22, 2024 08:31 11s
October 22, 2024 08:31 11s
ppo是否支持基于step打分的reward模型(类似math-shepherd-mistral-7b-prm）进行训练 label_issue #1382: Issue #5776 opened by wphtrying
October 22, 2024 08:07 11s
October 22, 2024 08:07 11s
请问通过程序调用llamafactory-cli执行训练，调用的程序怎样判断llamafactory-cli运行是否成功或失败 label_issue #1381: Issue #5775 opened by czhcc
October 22, 2024 05:15 11s
October 22, 2024 05:15 11s
fix test tests #1450: Commit 74a79cc pushed by hiyouga
October 22, 2024 04:35 8m 28s main
main
October 22, 2024 04:35 8m 28s
Qwen2-vl 推理时，图片分辨率高会报错 label_issue #1380: Issue #5773 opened by xyf0106
October 22, 2024 03:38 10s
October 22, 2024 03:38 10s
微调过后想要进行评估，该如何评估，计算blue和rouge分布，数据该如何自定义 label_issue #1379: Issue #5772 opened by jqtian123
October 22, 2024 03:32 12s
October 22, 2024 03:32 12s
fix #5768 tests #1449: Commit d155b70 pushed by hiyouga
October 22, 2024 03:06 4m 38s main
main
October 22, 2024 03:06 4m 38s
从checkpoint续训，导致oom label_issue #1378: Issue #5771 opened by Arcmoon-Hu
October 22, 2024 02:47 10s
October 22, 2024 02:47 10s
llama_pro二次预训练后的模型微调eval_loss为nan label_issue #1377: Issue #5770 opened by tammypi
October 22, 2024 01:35 11s
October 22, 2024 01:35 11s
distributed training: using GPU 0 to perform barrier as devices used by this process are currently unknown. label_issue #1376: Issue #5769 opened by hiennguyennq
October 21, 2024 18:31 16s
October 21, 2024 18:31 16s
Add llava med dataset tests #1448: Pull request #5746 synchronize by snova-supasani
October 21, 2024 16:06 Action required snova-supasani:shubhangiu/add-llava-med-finetuning
snova-supasani:shubhangiu/add-llava-med-finetuning
October 21, 2024 16:06 Action required
<video>查找判断问题BUG label_issue #1375: Issue #5768 opened by cqray1990
October 21, 2024 14:29 13s
October 21, 2024 14:29 13s
Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'") label_issue #1374: Issue #5767 opened by chester5610
October 21, 2024 10:30 10s
October 21, 2024 10:30 10s
运行代码后，数据处理一直为0% label_issue #1373: Issue #5766 opened by caoyaru123
October 21, 2024 10:26 15s
October 21, 2024 10:26 15s
doc里关于inference部分的说明，有个问题请教。 label_issue #1372: Issue #5765 opened by echoht
October 21, 2024 09:38 11s
October 21, 2024 09:38 11s
单论多图的数据集应该如何创建？ label_issue #1371: Issue #5764 opened by WoodPecker1111
October 21, 2024 08:38 13s
October 21, 2024 08:38 13s
华为NPU适配，依赖冲突。 label_issue #1370: Issue #5763 opened by yangyang6666
October 21, 2024 08:36 12s
October 21, 2024 08:36 12s
Clarification on cutoff_len and Image Scaling Parameters in Qwen2-VL finetune with LoRA config label_issue #1369: Issue #5762 opened by JackieQiang
October 21, 2024 08:09 14s
October 21, 2024 08:09 14s
llamafactory-cli运行原理 label_issue #1368: Issue #5761 opened by JusticeJason
October 21, 2024 07:52 12s
October 21, 2024 07:52 12s
做全参数SFT报错No module named 'transformers.models.gemma' label_issue #1367: Issue #5760 opened by RZFan525
October 21, 2024 07:30 13s
October 21, 2024 07:30 13s
请教下作者，目前新版代码关于cutoff_len是怎么处理的？ label_issue #1366: Issue #5759 opened by echoht
October 21, 2024 07:18 15s
October 21, 2024 07:18 15s
load_best_model_at_end=True ，多机多卡训练 label_issue #1365: Issue #5757 opened by w1051868626
October 21, 2024 03:29 10s
October 21, 2024 03:29 10s
有计划支持whisper、qwen2-audio之类的asr模型微调吗？ label_issue #1364: Issue #5756 opened by bjfk2006
October 21, 2024 03:20 12s
October 21, 2024 03:20 12s