-
Notifications
You must be signed in to change notification settings - Fork 3.3k
Issues: hiyouga/LLaMA-Factory
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
kto_pair not available error
pending
This problem is yet to be addressed
#4839
opened Jul 15, 2024 by
JianbangZ
1 task done
昇腾910b推理baichuan2-13B模型报错:The operator 'aten::isin.Tensor_Tensor_out' is not currently supported on the NPU backend and will 待解决
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#4836
opened Jul 15, 2024 by
fuqiang-benz
1 task done
Asecend910A推理glm4-9b-chat出现 NPU function error
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#4833
opened Jul 15, 2024 by
AlexYoung757
1 task done
已扩展词表的大模型推理导出问题
pending
This problem is yet to be addressed
#4832
opened Jul 15, 2024 by
add1211
1 task done
在.yaml文件设置不同的学习率,训练日志中total optimization steps不一样,是为什么呢?
pending
This problem is yet to be addressed
#4819
opened Jul 15, 2024 by
Silenceang
1 task done
Support precompute reference log probs for DPO training
pending
This problem is yet to be addressed
#4810
opened Jul 14, 2024 by
OnewayLab
128卡 A800 80G qwen2 7b cut_off 8192报错oom
pending
This problem is yet to be addressed
#4805
opened Jul 13, 2024 by
BobTsang1995
1 task done
Slow batched evals
pending
This problem is yet to be addressed
#4801
opened Jul 12, 2024 by
shreyaspimpalgaonkar
1 task done
FSDP-QLora w/ DeepSeek-v2-lite dones't work on 4 GPUs
bug
Something isn't working
pending
This problem is yet to be addressed
#4785
opened Jul 12, 2024 by
Jiayi-Pan
1 task done
Qwen72B在16NPU卡上爆显存
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#4758
opened Jul 10, 2024 by
sweetning0809
1 task done
使用vllm时支持bitsandbytes量化
pending
This problem is yet to be addressed
#4751
opened Jul 10, 2024 by
JJJJerry
Enable Contamination-Free Packaging Method During Pretraining
pending
This problem is yet to be addressed
#4744
opened Jul 9, 2024 by
kostum123
1 task done
Faild to save the gptq quantized weight on Qwen2 72B.
pending
This problem is yet to be addressed
#4737
opened Jul 9, 2024 by
fzp0424
1 task done
Phi-3-small Different Chat Template
pending
This problem is yet to be addressed
#4712
opened Jul 7, 2024 by
maksimstw
1 task done
Invalid device string: 'float32'
pending
This problem is yet to be addressed
#4698
opened Jul 6, 2024 by
OnewayLab
1 task done
Feature request: is Adam-mini optimizer worth adding?
pending
This problem is yet to be addressed
#4696
opened Jul 5, 2024 by
jim-plus
1 task done
疑问:历史消息在训练时可以只作为上文不参与模型的预测吗?~
enhancement
New feature or request
pending
This problem is yet to be addressed
#4684
opened Jul 4, 2024 by
ylsdamxssjxxdd
1 task done
qwen2 72b 910b lora后merge生成的权重 推理失败
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#4659
opened Jul 3, 2024 by
wphtrying
1 task done
ValueError: Failed to convert pandas DataFrame to Arrow Table from file
pending
This problem is yet to be addressed
#4650
opened Jul 2, 2024 by
fzp0424
1 task done
RuntimeError: "addmm_impl_cpu_" not implemented for 'Half' 华为910 命令行推理报错
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#4622
opened Jun 30, 2024 by
apachemycat
1 task done
fsdp + DPO + fullyfintune会报错
bug
Something isn't working
pending
This problem is yet to be addressed
#4608
opened Jun 28, 2024 by
qy1026
1 task done
[PPU]大佬有对ppu环境进行过测试么
pending
This problem is yet to be addressed
#4606
opened Jun 28, 2024 by
willionZS
1 task done
关于npu训练模型总结以及疑问
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#4388
opened Jun 20, 2024 by
sweetning0809
1 task done
[Feature request] 支持Qwen-VL
pending
This problem is yet to be addressed
#4375
opened Jun 19, 2024 by
marko1616
Previous Next
ProTip!
Adding no:label will show everything without a label.