-
Notifications
You must be signed in to change notification settings - Fork 8.9k
- #4614 · hiyouga opened
on Jun 28, 2024 - #4388 · sweetning0809 opened
on Jun 20, 2024 34 - #4341 · mapix opened
on Jun 17, 2024 7
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
Qwen3-8B-Thinking在sft以后chat会话中，直接输出了<think>
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10617 In hiyouga/LlamaFactory;训练中eval的一些疑问
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10611 In hiyouga/LlamaFactory;Flash attention broken in transformers 5.6.0
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10610 In hiyouga/LlamaFactory;Bug in gradio webui
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10609 In hiyouga/LlamaFactory;Qwen3-VL 多视频训练时，如果不同视频采样帧数不同，会出现 video tokens 与 features 数量不匹配
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10608 In hiyouga/LlamaFactory;合并lora微调后模型+vllm部署与直接使用llamafactory分别加载基座模型与checkpoint建立的接口推理效果不一致
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10596 In hiyouga/LlamaFactory;Unsloth vs. LlamaFactory - incompatible torch
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10593 In hiyouga/LlamaFactory;Qwen3.5-122B-A10B lora SFT，仅把lora_target从all改为q_proj, v_proj，加载模型出现Cuda out of memory
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10591 In hiyouga/LlamaFactory;How to set a random seed in the weibuUI interface to control randomness
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10581 In hiyouga/LlamaFactory;训练Qwen3.5-4B时报错了
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10580 In hiyouga/LlamaFactory;- Status: Open.#10568 In hiyouga/LlamaFactory;
scripts/megatron_merge.py,转换报错,qwen3.5_27b
bugSomething isn't workingSomething isn't workingpendingThis problem is yet to be addressedThis problem is yet to be addressedStatus: Open.#10565 In hiyouga/LlamaFactory;