[go: nahoru, domu]
Skip to content

Issues: hiyouga/LLaMA-Factory

🚨FAQs | 常见问题🚨
#4614 opened Jun 28, 2024 by hiyouga
Open
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.

Sign up for GitHub

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

46 Open 4,049 Closed
46 Open 4,049 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

关于对话模板作用以及其在lm-evaluation-harness仓库下对评测效果影响的问题 pending This problem is yet to be addressed
#4618 opened Jun 29, 2024 by marvelcell
1 task done
DPO 训练时，prompt 与 answer 拼接问题，导致cutoff_length这一超参数无法对数据进行有效截断。 pending This problem is yet to be addressed
#4617 opened Jun 29, 2024 by THZdyjy
🚨FAQs | 常见问题🚨 good first issue Good for newcomers
#4614 opened Jun 28, 2024 by hiyouga
华为NPU训练不了，用的例子里的训练脚本，镜像也是官方镜像 npu This problem is related to NPU devices pending This problem is yet to be addressed
#4610 opened Jun 28, 2024 by apachemycat
1 task done
3
ppo合并失败 pending This problem is yet to be addressed
#4609 opened Jun 28, 2024 by luowei0701
1 task done
1
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
1
[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
8卡A800全参数预训练GLM4-9B-base,使用bf16,loss在暴涨后突然消失 pending This problem is yet to be addressed
#4597 opened Jun 28, 2024 by lclcjj
1 task done
Cutoff Length only followed for chosen response in Pairwise Data for DPO pending This problem is yet to be addressed
#4402 opened Jun 20, 2024 by niravlg
1 task done
1
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
9
[Feature request] 支持Qwen-VL pending This problem is yet to be addressed
#4375 opened Jun 19, 2024 by marko1616
1
Function tool calling inference without llama-factory openai style api. pending This problem is yet to be addressed
#4364 opened Jun 18, 2024 by svjack
1 task done
Ascend卡上无法训练deepseek模型 是否支持呢 npu This problem is related to NPU devices pending This problem is yet to be addressed
#4361 opened Jun 18, 2024 by sweetning0809
1 task done
3
可以支持英伟达的新模型Nemotron 340B吗? pending This problem is yet to be addressed
#4313 opened Jun 16, 2024 by laosuan
1 task done
Jamba & Deepspeed zero-3 pending This problem is yet to be addressed
#4300 opened Jun 15, 2024 by lwang2070
1 task done
4
请问是否会在框架内集成RLOO算法，最新的online RLHF？ enhancement New feature or request pending This problem is yet to be addressed
#4287 opened Jun 14, 2024 by ArcherShirou
1 task done
2
在npu上，对大模型用zero3进行全参微调，初始换参数很大，是什么原因造成的？ npu This problem is related to NPU devices pending This problem is yet to be addressed
#4272 opened Jun 14, 2024 by fjw1049
1 task done
昇腾卡训练不支持offload npu This problem is related to NPU devices pending This problem is yet to be addressed
#4146 opened Jun 7, 2024 by wangbing35
1 task done
1
data.utils.split_dataset中的切分和随机逻辑能否迁移到data.loader.get_dataset中? pending This problem is yet to be addressed
#4140 opened Jun 7, 2024 by luoqishuai
1 task done
【NPU】GLM-4-9B-Chat PPO 出错 npu This problem is related to NPU devices pending This problem is yet to be addressed
#4135 opened Jun 7, 2024 by hunterhome
1 task done
5
sft+freeze训练internlm2-base-7b报错，RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn npu This problem is related to NPU devices pending This problem is yet to be addressed
#4101 opened Jun 6, 2024 by 1737686924
1 task done
Unable to run model.generate() for MoD model pending This problem is yet to be addressed
#4063 opened Jun 4, 2024 by Zkli-hub
1 task done
2
用openai库 请求时，流式请求时缺stream_options={"include_usage": True}的处理，用于计算流式tokens pending This problem is yet to be addressed
#3998 opened May 30, 2024 by sasicDHH
1 task done
Feature suggestion: cutoff_len could optionally drop too long examples from dataset. pending This problem is yet to be addressed
#3995 opened May 30, 2024 by s4s0l
1
How to specify eval set during training process? pending This problem is yet to be addressed
#3974 opened May 30, 2024 by may012345
1 task done
ProTip! Follow long discussions with comments:>50.