modelscope/ms-swift
Use PEFT or Full-parameter to finetune 300+ LLMs or 80+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
PythonApache-2.0
Pinned issues
Issues
- 2
“训练推理界面”后点击“通过 API 使用”时报错。
#1932 opened by KnightLancelot - 1
NPU qwen2模型推理报错
#1951 opened by JiayuQiao - 2
swift 中如何设置模型内部参数,如internvl中的max_dynamic_patch
#1953 opened by zws-2019 - 6
internvl2-llama3-76b 微调报错
#1892 opened by zhangfan-algo - 5
dpo internvl2存在mismatch
#1930 opened by Ranking666 - 4
Training stops for `KTO` after model loads into memory.
#1938 opened by Aunali321 - 2
qwen2_audio_7b_instruct利用VLLM推理错误
#1937 opened by huangzj421 - 4
关于 Qwen2_VL-2B 微调时显存不足的问题
#1935 opened by Betty-J - 9
- 1
Qwen2-VL-7B-instruct 微调报错:RuntimeError: CUDA error: too many resources requested for launch
#1927 opened by xiajinxiong - 5
TypeError: Qwen2ForCausalLM.forward() got an unexpected keyword argument '_data'
#1929 opened by xiamaozi11 - 1
Qwen2-VL-7B-Instruct Video inference
#1920 opened by wangli68 - 3
swift infer的时候,传递do_sample参数不起作用
#1943 opened by baibaiw5 - 2
使用自定数据集DPO mllm时报错KeyError: 'prompt'
#1922 opened by SparrowZheyuan18 - 2
请问是否支持在NPU上训练多模态大模型
#1941 opened by ChingKwanCheung - 4
微调glm4v, 给glm4v的视觉部分都添加了checkpoint, 但是还是显存溢出(lora_target_modules 设置为'ALL' )
#1934 opened by samaritan1998 - 1
Cannot get model_type from the deploy service
#1904 opened by Harry-zzh - 0
BUG:init_lora lead to the wrong distribute?
#1944 opened by bonre - 3
两张V100微调qwen2-7b,单卡微调正常,双卡微调出现RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
#1882 opened by kksmi - 0
MooER audio support request
#1919 opened by seetimee - 4
qwen2-vl-2b-instruct微调报错ValueError: push_best is not a valid HubStrategy, please select one of ['end', 'every_save', 'checkpoint', 'all_checkpoints']
#1917 opened by learn01one - 1
GLM4V-9B微调后,直接调用微调的模型出错:ValueError: The following `model_kwargs` are not used by the model: ['images'] (note: typos in the generate arguments will also show up in this list)
#1902 opened by tw-repository - 1
Merge LoRA & 量化部分 支持bnb量化嘛
#1895 opened by kelenlv - 3
如何调整训练损失函数类型?自定义损失函数?(Custom loss function)
#1891 opened by XiaoMaGe-hero - 6
qwen2-vl微调使用flash_attn报错
#1887 opened by zhangfan-algo - 1
dpo微调internvl2
#1886 opened by Ranking666 - 4
请教一下,图片、视频等多模态数据超长应该怎么截断?
#1876 opened by HuiResearch - 15
- 1
- 4
minicpm-V-2最佳实践,执行推理时,模型不输出任何结果
#1863 opened by hxzl-98 - 0
streaming模式读取数据,显存利用率很低
#1939 opened by guozhiyao - 1
lr_scheduler_type
#1894 opened by mc-lan - 0
qwen2-vl-chat-instruct示例数据格式
#1896 opened by Guangming92 - 1
dpo微调与zero3不兼容
#1899 opened by zhangfan-algo - 2
llava-llama-3-8b-v1_1 AttributeError: 'NoneType' object has no attribute 'get_output_embeddings'
#1911 opened by thisiskofi - 1
【新增功能需求】 Internvl2模型+VLLM 后端实现 异步客户端请求的Video 推理功能
#1921 opened by PancakeAwesome - 0
视觉模块支持gradient_checkpointing
#1928 opened by samaritan1998 - 0
qwen2-vl-2b-instruct使用自定义数据集微调出现DatasetGenerationError
#1918 opened by lgy0404 - 0
minicpm-v-v2.6评测出现结果为0情况
#1924 opened by zhudongmei123 - 0
Support for Fine-Tuning Best Practices with LLaVA-OV
#1923 opened by YoungjaeDev - 3
- 2
qwen2-vl-2b-instruct微调报错:importlib.metadata.PackageNotFoundError: No package metadata was found for The 'qwen_vl_utils' distribution was not found and is required by this application.
#1905 opened by lgy0404 - 0
AssertionError: DeepSpeed does not recognize LR scheduler WarmupCosineLR
#1906 opened by Jintao-Huang - 15
- 2
ImportError: cannot import name 'LlavaOnevisionForConditionalGeneration' from 'transformers'
#1878 opened by Lopa07 - 2
internvl-40b模型微调后推理时报错
#1881 opened by ymlab - 1
How to freeze the ViT part during full parameter fine-tuning of Qwen2-vl?
#1879 opened by Jintao-Huang - 0
Memory(not GPU RAM) exceeds when using 'swift deploy'
#1866 opened by VenusHui - 0
qwen2-vl fine-tuning error: module 'torch.nn' has no attribute 'RMSNorm'
#1870 opened by Jintao-Huang - 0
deepspeed-zero3: Input should be a valid integer, got a number with a fractional part [type=int_from_float, input_value=11560550.4, input_type=float]
#1862 opened by Jintao-Huang