Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
3,597 workflow runs
3,597 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[version] support transformers 4.48 & Byebye python 3.8 tests #1885: Pull request #6628 synchronize by hiyouga
January 30, 2025 16:21 8m 40s hiyouga/upd_hf_4_48
hiyouga/upd_hf_4_48
January 30, 2025 16:21 8m 40s
[webui] improve webui & reasoning mode (#6778) tests #1884: Commit 45e68b9 pushed by hiyouga
January 30, 2025 16:09 8m 41s main
main
January 30, 2025 16:09 8m 41s
[webui] improve webui & reasoning mode tests #1883: Pull request #6778 opened by hiyouga
January 30, 2025 16:02 8m 51s hiyouga/improve_r1
hiyouga/improve_r1
January 30, 2025 16:02 8m 51s
Fp8 quantization label_issue #2133: Issue #6777 opened by HARISHSENTHIL
January 29, 2025 09:28 11s
January 29, 2025 09:28 11s
Template deepseekr1 does not exist label_issue #2132: Issue #6776 opened by Fangkang515
January 29, 2025 07:35 9s
January 29, 2025 07:35 9s
[model] add deepseek-R1 & show think process (#6767) tests #1882: Commit 28417f8 pushed by hiyouga
January 29, 2025 04:16 8m 29s main
main
January 29, 2025 04:16 8m 29s
有计划支持Deepseek的janus pro微调么 label_issue #2131: Issue #6775 opened by mkygogo
January 28, 2025 15:58 10s
January 28, 2025 15:58 10s
Add DeepSeek-R1 and its distilled model (Qwen&Llama) tests #1881: Pull request #6767 synchronize by Qwtdgh
January 28, 2025 14:45 7m 40s Qwtdgh:main
Qwtdgh:main
January 28, 2025 14:45 7m 40s
Add DeepSeek-R1 and its distilled model (Qwen&Llama) tests #1880: Pull request #6767 synchronize by Qwtdgh
January 28, 2025 13:55 Action required Qwtdgh:main
Qwtdgh:main
January 28, 2025 13:55 Action required
Add DeepSeek-R1 and its distilled model (Qwen&Llama) tests #1879: Pull request #6767 synchronize by Qwtdgh
January 28, 2025 13:46 Action required Qwtdgh:main
Qwtdgh:main
January 28, 2025 13:46 Action required
Q_APOLLO? label_issue #2130: Issue #6774 opened by inflatebot
January 28, 2025 12:47 10s
January 28, 2025 12:47 10s
When the part of Running training started, running speed is very low. Could anyone solve this problem？ thanks label_issue #2129: Issue #6773 opened by lxcxjxhx1
January 28, 2025 06:01 12s
January 28, 2025 06:01 12s
Qwen2.5-VL support label_issue #2128: Issue #6772 opened by tristanwqy
January 28, 2025 03:49 10s
January 28, 2025 03:49 10s
MiniCPM-o-2_6视频处理存在问题 label_issue #2127: Issue #6770 opened by jinzhuoran
January 27, 2025 14:54 11s
January 27, 2025 14:54 11s
Multiple Dataset Training Help label_issue #2126: Issue #6769 opened by JiwenJ
January 27, 2025 13:18 10s
January 27, 2025 13:18 10s
Qwen2-VL多图推理 label_issue #2125: Issue #6768 opened by XiruiTeng
January 27, 2025 12:50 12s
January 27, 2025 12:50 12s
Add DeepSeek-R1 and its distilled model (Qwen&Llama) tests #1878: Pull request #6767 opened by Qwtdgh
January 27, 2025 03:48 Action required Qwtdgh:main
Qwtdgh:main
January 27, 2025 03:48 Action required
training_args.parallel_mode param questions label_issue #2124: Issue #6766 opened by boyu-zhu
January 27, 2025 02:47 12s
January 27, 2025 02:47 12s
[bug] 用llamafactory的examples/train_qlora/llama3_lora_sft_otfq.yaml微调后词表里多了一个token(<|eom_id|>) label_issue #2123: Issue #6765 opened by iyjian
January 26, 2025 14:03 9s
January 26, 2025 14:03 9s
ValueError: Can't find 'adapter_config.json' at '../models/llama3_1B' label_issue #2122: Issue #6764 opened by zhangguoxin1
January 26, 2025 09:42 9s
January 26, 2025 09:42 9s
希望支持RFT微调方法。 label_issue #2121: Issue #6763 opened by bhnan
January 26, 2025 05:46 8s
January 26, 2025 05:46 8s
One of the subprocesses has abruptly died during map operation.To debug the error, disable multiprocessing. 无论numworkers多大都没用 label_issue #2120: Issue #6762 opened by miaowuawa
January 25, 2025 15:13 11s
January 25, 2025 15:13 11s
does save_strategy conflicts with save_total_limit? label_issue #2119: Issue #6761 opened by VoiceBeer
January 25, 2025 14:39 10s
January 25, 2025 14:39 10s
deepspeed z3训练一直报错 label_issue #2118: Issue #6760 opened by likeaTT
January 25, 2025 13:06 13s
January 25, 2025 13:06 13s
全参数微调的结果如何作为后续LoRA微调的base model label_issue #2117: Issue #6759 opened by sizhewan
January 25, 2025 10:13 9s
January 25, 2025 10:13 9s