Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
3,551 workflow runs
3,551 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

qwen2_5 function call template 不一致 label_issue #2105: Issue #6744 opened by onbncbjocp68898
January 23, 2025 07:14 11s
January 23, 2025 07:14 11s
Running tokenizer on dataset (num_proc=16)报错。 TypeError: argument of type 'NoneType' is not iterable #667 label_issue #2104: Issue #6743 opened by houliping
January 23, 2025 06:26 11s
January 23, 2025 06:26 11s
训练出错，cuda缺少libcusparse.so.11，更新重装都没用，请大佬帮忙看看，感谢 label_issue #2103: Issue #6742 opened by sgg-comeon
January 23, 2025 05:15 10s
January 23, 2025 05:15 10s
python scripts/vllm_infer.py执行模型批量推理报错Caught signal 8 (Floating point exception: integer divide by zero) label_issue #2102: Issue #6741 opened by zdw-111
January 23, 2025 03:50 8s
January 23, 2025 03:50 8s
python scripts/vllm_infer.py方式进行模型批量推理报错 label_issue #2101: Issue #6740 opened by zdw-111
January 23, 2025 03:44 13s
January 23, 2025 03:44 13s
command 'llamafactory-cli webui' failed to start if HTTP_PROXY is set label_issue #2100: Issue #6739 opened by qiangyt
January 22, 2025 15:59 12s
January 22, 2025 15:59 12s
请求支持 qwen2-audio label_issue #2099: Issue #6738 opened by superFilicos
January 22, 2025 13:57 14s
January 22, 2025 13:57 14s
请问：是否支持微调 DeepSeek-R1-Distill 系列模型？ label_issue #2098: Issue #6737 opened by CsBoBoNice
January 22, 2025 07:55 15s
January 22, 2025 07:55 15s
After lora training, model repeat output ! label_issue #2097: Issue #6736 opened by VectorGready
January 22, 2025 07:39 15s
January 22, 2025 07:39 15s
windows环境 使用 chat 对话功能 无限循环的问题 label_issue #2096: Issue #6735 opened by 255724285
January 22, 2025 06:24 9s
January 22, 2025 06:24 9s
训练出错，参数参照的网上视频，工具也完整，请大佬帮忙看看问题，谢谢 label_issue #2095: Issue #6733 opened by sgg-comeon
January 22, 2025 00:00 12s
January 22, 2025 00:00 12s
How to jump a single sample？ label_issue #2094: Issue #6732 opened by sxj1215
January 21, 2025 22:41 10s
January 21, 2025 22:41 10s
冻结特定的几层 label_issue #2093: Issue #6731 opened by shutttttdown
January 21, 2025 16:14 10s
January 21, 2025 16:14 10s
dpo 训练数据格式报错 label_issue #2092: Issue #6730 opened by wphtrying
January 21, 2025 13:07 11s
January 21, 2025 13:07 11s
910下面进行dpo训练 reward accuracy value只有0或者1 label_issue #2091: Issue #6729 opened by wphtrying
January 21, 2025 11:23 10s
January 21, 2025 11:23 10s
910下面进行dpo训练 reward accuracy value只有0或者1 label_issue #2090: Issue #6728 opened by wphtrying
January 21, 2025 11:21 12s
January 21, 2025 11:21 12s
qwen2.5-32B-Instruct模型2机npu 910B训练结束后，保存模型时失败 label_issue #2089: Issue #6726 opened by chriszhangmq
January 21, 2025 08:40 13s
January 21, 2025 08:40 13s
windows下微调llama3.1-instruction 开始训练后报错 无法启动微调 label_issue #2088: Issue #6725 opened by LJXCMQ
January 21, 2025 08:30 9s
January 21, 2025 08:30 9s
预训练格式和sft微调格式是否可以同时进行微调？ label_issue #2087: Issue #6724 opened by weilx2267
January 21, 2025 07:50 11s
January 21, 2025 07:50 11s
fix: avoid redundant normalization in DPO's SFT loss calculation (#6722) tests #1876: Commit 0f45982 pushed by hiyouga
January 21, 2025 05:38 10m 23s main
main
January 21, 2025 05:38 10m 23s
fix: avoid redundant normalization in DPO's SFT loss calculation tests #1875: Pull request #6722 opened by yinpu
January 21, 2025 04:28 7m 35s yinpu:main
yinpu:main
January 21, 2025 04:28 7m 35s
为什么读取了全部的训练数据，但训练时只用可很小一部分？ label_issue #2086: Issue #6721 opened by chingtanpiu
January 21, 2025 04:21 11s
January 21, 2025 04:21 11s
llamafactory部署在服务器上，webui无法获取到数据集，请大佬帮忙，谢谢 label_issue #2085: Issue #6720 opened by sgg-comeon
January 21, 2025 01:27 11s
January 21, 2025 01:27 11s
label smoothing 支持 label_issue #2084: Issue #6719 opened by 652994331
January 20, 2025 15:57 12s
January 20, 2025 15:57 12s
please add bitune support label_issue #2083: Issue #6718 opened by chaitu0032
January 20, 2025 14:29 14s
January 20, 2025 14:29 14s