LlamaFactory · Issues· 1156 open

新手提问：微调 Qwen2.5-0.5B 最低需要什么显卡配置？

目前支持Qwen3.8的sft吗？

Cannot import name 'load_and_register_kernel' from 'transformers.integrations.hub_kernels'

[HELP] Runable solution of RTX 5090 GPU + Linux Driver version + Pytorch version + Deepspeed version for LLM finetuning

在GPU 5090上使用docker安装llama factory 出现问题

Python 3.14 support addition

about ppo unwrap_model

[FEAT] Support fine‑tuning for Qwen3.8‑27B‑Instruct model

[First-time contributor] Looking for beginner-friendly issues to contribute

_calculate_timestamps参数使用

单机多卡，开启swanlab日志输出，报错：[rank0]: raise RuntimeError("No active Run. Call swanlab.init() first.")

[BUG] KTO with mrope models (Qwen3.5 family) crashes at step 0: "Multimodal data was passed ... but mm_token_type_ids is missing"

bug: TypeError in collator.py — _slice_mm_inputs_for_sample called with sample_idx= but param is batch_idx

[Bug] DPO training crashes with Qwen3.5-35B-A3B (MoE VLM): TypeError: expected Tensor as element 0 in argument 0, but got list in collator

Unauthenticated SSRF via image_url in the API server, bypassing check_ssrf_url by redirect and DNS rebinding (incomplete fix)