Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

label_issue

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
label_issue.yml
1,976 workflow runs
1,976 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Llama Factory Finetuning label_issue #2074: Issue #6704 opened by yaosheng-zhang
January 19, 2025 04:01 12s
January 19, 2025 04:01 12s
微调LLAMA 3.2 -8B时出现ValueError: This model does not support image input. Please check whether the correct template is used. label_issue #2073: Issue #6703 opened by bboyliang
January 18, 2025 17:00 9s
January 18, 2025 17:00 9s
Repo ID Format label_issue #2072: Issue #6702 opened by giruuuuj
January 18, 2025 16:56 13s
January 18, 2025 16:56 13s
Param Size Mismatch after Fine-tuned on Llama-3-8B-Instruct label_issue #2071: Issue #6700 opened by bw-wang19
January 18, 2025 14:39 10s
January 18, 2025 14:39 10s
Size mismatch error in the middle of training label_issue #2070: Issue #6699 opened by NicoZenith
January 18, 2025 14:24 10s
January 18, 2025 14:24 10s
Qwen2VL 增量预训练脚本 label_issue #2069: Issue #6697 opened by Road2Redemption
January 18, 2025 10:24 9s
January 18, 2025 10:24 9s
colab.research.google.com 环境中 使用 web 页面的问题 label_issue #2068: Issue #6695 opened by zoutao212
January 18, 2025 08:49 12s
January 18, 2025 08:49 12s
昇腾NPU单机多卡训练Qwen2-VL-2B报错 label_issue #2067: Issue #6694 opened by sugarandgugu
January 18, 2025 07:03 12s
January 18, 2025 07:03 12s
自动被killed且无任何报错信息 label_issue #2066: Issue #6687 opened by duyu09
January 17, 2025 11:11 12s
January 17, 2025 11:11 12s
DPO 能否支持数据packing label_issue #2065: Issue #6686 opened by yinzhijian
January 17, 2025 08:31 11s
January 17, 2025 08:31 11s
deepspeed 容器环境下no-ssh多机多卡训练 label_issue #2064: Issue #6685 opened by Justin-12138
January 17, 2025 07:05 10s
January 17, 2025 07:05 10s
qwen0.5微调改变自我认知导出后加载模型又变回去了 label_issue #2063: Issue #6681 opened by qzy-github
January 17, 2025 03:49 10s
January 17, 2025 03:49 10s
adam_mini error ？ during qwen 7b full sft training label_issue #2062: Issue #6680 opened by chuangzhidan
January 17, 2025 03:41 10s
January 17, 2025 03:41 10s
dpo训练出现重复和随机的英文乱码 label_issue #2061: Issue #6679 opened by liuanping
January 17, 2025 03:26 9s
January 17, 2025 03:26 9s
精确的json格式输出 label_issue #2060: Issue #6678 opened by cqray1990
January 17, 2025 03:21 11s
January 17, 2025 03:21 11s
How to print train mfu? label_issue #2059: Issue #6677 opened by marks221b
January 17, 2025 02:49 10s
January 17, 2025 02:49 10s
CUDA out of memory when evaluating model label_issue #2058: Issue #6676 opened by HeroSong666
January 17, 2025 01:27 10s
January 17, 2025 01:27 10s
loss gradient when run hidden_states = hidden_states.to(torch.float32) label_issue #2057: Issue #6675 opened by hanlinxuy
January 16, 2025 12:40 11s
January 16, 2025 12:40 11s
请教：pretrain如何配置多副本 label_issue #2056: Issue #6674 opened by ltm920716
January 16, 2025 11:05 13s
January 16, 2025 11:05 13s
为什么 yaml中设置的lora_rank和adapter config文件的lora_rank有2倍的关系，以哪个为准？ label_issue #2055: Issue #6672 opened by chuangzhidan
January 16, 2025 10:24 14s
January 16, 2025 10:24 14s
昇腾910B上进行推理时，调不了NPU卡 label_issue #2054: Issue #6671 opened by winni0
January 16, 2025 09:52 12s
January 16, 2025 09:52 12s
image_resolution 参数文档是不是写错了？ label_issue #2053: Issue #6670 opened by rover5056
January 16, 2025 09:28 18s
January 16, 2025 09:28 18s
Qwen2Moe zero3卡住的问题，已找到原因 label_issue #2052: Issue #6669 opened by MrLittleB
January 16, 2025 09:10 14s
January 16, 2025 09:10 14s
RUNNING_LOG 的路径问题 label_issue #2051: Issue #6668 opened by zyp-byte
January 16, 2025 06:55 12s
January 16, 2025 06:55 12s
windows多卡微调 label_issue #2050: Issue #6667 opened by q872839000
January 16, 2025 05:47 13s
January 16, 2025 05:47 13s