Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
3,155 workflow runs
3,155 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Max sequence length" corresponds to which parameter? label_issue #1810: Issue #6325 opened by Zixuan-Fu
December 13, 2024 02:53 11s
December 13, 2024 02:53 11s
这行代码我找不到函数的出处，step函数在哪里定义的 label_issue #1809: Issue #6324 opened by dahaogewsh
December 13, 2024 00:29 11s
December 13, 2024 00:29 11s
InternVL2.5-8B label_issue #1808: Issue #6322 opened by saeedkhaki92
December 12, 2024 18:35 12s
December 12, 2024 18:35 12s
Add trust_remote_code Parameter and Set Default to False tests #1641: Pull request #5819 synchronize by yafshar
December 12, 2024 17:05 Action required yafshar:remote_code
yafshar:remote_code
December 12, 2024 17:05 Action required
fix mrope tests #1640: Commit 2811814 pushed by hiyouga
December 12, 2024 15:08 7m 55s main
main
December 12, 2024 15:08 7m 55s
NLG评估DPO，不输出结果 label_issue #1807: Issue #6321 opened by sunxiaoyu12
December 12, 2024 13:50 13s
December 12, 2024 13:50 13s
Add trust_remote_code Parameter and Set Default to False tests #1639: Pull request #5819 synchronize by yafshar
December 12, 2024 13:16 Action required yafshar:remote_code
yafshar:remote_code
December 12, 2024 13:16 Action required
微调后倒出的模型使用llama.cpp生成gguf文件后导入ollama中每次ollama都胡乱回答 label_issue #1806: Issue #6320 opened by qq1273834091
December 12, 2024 09:40 12s
December 12, 2024 09:40 12s
全量微调后，如何起预测服务？目前只看到lora微调后起预测服务的示例 label_issue #1805: Issue #6319 opened by JoyceChen36
December 12, 2024 09:33 11s
December 12, 2024 09:33 11s
Merge pull request #6317 from hiyouga/hiyouga/qwenvl_mrope tests #1638: Commit c708ebd pushed by hiyouga
December 12, 2024 09:22 7m 43s main
main
December 12, 2024 09:22 7m 43s
使用Qwen数据模板，微调input构造不合理 label_issue #1804: Issue #6318 opened by phbst
December 12, 2024 09:17 14s
December 12, 2024 09:17 14s
[model] fix: qwen2vl mrope tests #1637: Pull request #6317 opened by hiyouga
December 12, 2024 09:12 6m 47s hiyouga/qwenvl_mrope
hiyouga/qwenvl_mrope
December 12, 2024 09:12 6m 47s
padding_side的设置 label_issue #1803: Issue #6316 opened by lllabmaster
December 12, 2024 09:08 14s
December 12, 2024 09:08 14s
昇腾训练千问2-7B DPO下设置batch_size问题求助 label_issue #1802: Issue #6315 opened by liuanping
December 12, 2024 05:48 10s
December 12, 2024 05:48 10s
为什么DPO训练时ref_model不指定为初始的SFT完的模型，而是用每个batch参数更新后的policy model来初始化呢？ label_issue #1801: Issue #6314 opened by lufanma
December 12, 2024 03:18 14s
December 12, 2024 03:18 14s
support telechat2 model tests #1636: Pull request #6313 opened by ge-xing
December 12, 2024 01:41 Action required ge-xing:main
ge-xing:main
December 12, 2024 01:41 Action required
关于sharegpt的数据格式的loss 计算，可能有问题 label_issue #1800: Issue #6312 opened by yangchao-zhou
December 11, 2024 09:42 12s
December 11, 2024 09:42 12s
单机多卡报错 label_issue #1799: Issue #6311 opened by 122550888
December 11, 2024 09:42 15s
December 11, 2024 09:42 15s
Add PEFT add_weighted_adapter() Function for Merging Multiple Adapters tests #1635: Pull request #6310 synchronize by Dlemonha
December 11, 2024 08:53 Action required Dlemonha:dwt_llama_factory
Dlemonha:dwt_llama_factory
December 11, 2024 08:53 Action required
Add PEFT add_weighted_adapter() Function for Merging Multiple Adapters tests #1634: Pull request #6310 opened by Dlemonha
December 11, 2024 08:37 Action required Dlemonha:dwt_llama_factory
Dlemonha:dwt_llama_factory
December 11, 2024 08:37 Action required
CTyunOS，命令“ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml”出错 label_issue #1798: Issue #6309 opened by y149604146
December 11, 2024 08:07 11s
December 11, 2024 08:07 11s
Should we support TGI-v3 serving model integration? label_issue #1797: Issue #6308 opened by phanxuanphucnd
December 11, 2024 07:48 10s
December 11, 2024 07:48 10s
llamafactory-cli webchat推理速度非常慢 label_issue #1796: Issue #6307 opened by eyexin
December 11, 2024 02:23 14s
December 11, 2024 02:23 14s
添加早停机制 label_issue #1795: Issue #6306 opened by huangshimai
December 11, 2024 02:23 19s
December 11, 2024 02:23 19s
Help label_issue #1794: Issue #6304 opened by Bing-a-ling7
December 10, 2024 13:52 12s
December 10, 2024 13:52 12s