InternLM/InternLM-XComposer
InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.
Python
Issues
- 0
使用lora微调后变成了复读机 After lora fine tuning, my model repeat the last sentence again and again
#324 opened by Kyoani-0718 - 2
InternLM-XComposer2-4KHD-7B 多卡推理
#274 opened by Cloopen-ReLiNK - 0
Not able to generate images
#323 opened by JosephKJ - 1
RuntimeError: mat1 and mat2 must have the same dtype, but got Float and Half
#317 opened by ulrika2cyl - 1
Multi-GPU inference
#322 opened by Han230104 - 0
generate函数代码问题
#321 opened by Zking668 - 0
InternLM-XComposer能否转换为TensorRT-llm的模型
#320 opened by thzyyx - 2
7B版本无法多卡运行
#303 opened by ybshaw - 0
grounding数据
#319 opened by sxlyiyiyi - 4
lora微调后的模型权重要如何在finetune.py中加载，进行二次微调
#279 opened by dle666 - 0
Lora微调4kHD模型需要的最小显存数？
#318 opened by ZhuangPeiyu - 0
- 0
关于多图微调以及推理问题
#315 opened by zhangye0402 - 11
- 1
全参数微调需要显存？以及多卡模型分布的问题。
#314 opened by hekaijie123 - 0
About PLora
#313 opened by decreasbetter - 6
我的机器无法连接到huggingface，但是下载了离线clip-vit无法使用
#295 opened by deku0818 - 3
- 0
Error occurred while loading the 4KHD model.
#310 opened by XueFengHF - 3
4khd-7b 多图sft时报错
#311 opened by zws-2019 - 0
请问4KHD版本的有无推出量化版本的计划？
#309 opened by ZhuangPeiyu - 1
Some errors:ValueError: Tokenizer class InternLMXComposerTokenizer does not exist or is not currently imported.
#308 opened by Shuweis - 0
Get the embeddings of the image.
#307 opened by xinyanghuang7 - 0
- 0
Error running 4khd inference
#304 opened by ChorlingLau - 0
url update in build_mlp.py
#302 opened by nzomi - 0
Output of `interleav_wrap_chat`
#301 opened by wlin-at - 5
请问XComposer2-VL现在支持多图输入吗？
#297 opened by zhourax - 2
When will the proj and vit freeze?
#273 opened by OpenJarvisAI - 0
Unified Prompt in ShareGPT4V
#299 opened by aleeyang - 1
MMBench评估代码报错
#298 opened by sczlmy - 3
webui运行internlm-xcomposer2-4khd-7b时报错
#286 opened by blackblue9 - 2
为什么用4K模型训练时loss是0？
#285 opened by zweiqi - 2
- 3
vit.vision_tower.vision_model.post_layernorm.weight & bias NOT initialized?
#296 opened by JasonLeeFdu - 2
Training error
#284 opened by LoFiApostasy - 4
Questions about img_size (224, 224) and (336, 336)
#282 opened by cocoshe - 0
InternLM-XComposer2-4KHD对中文文本图像识别和理解能力怎么样？
#293 opened by lhanchao777 - 2
Fine-tune Support for InternLM-XComposer2-4KHD-7B
#269 opened by babla9 - 7
- 3
微调internlm-xcomposer2-4khd-7b出错
#288 opened by 2132660698 - 1
推理的时候找不到模型文件中pytorch_model.bin
#280 opened by douyh - 6
train模式和test模式差别很大
#276 opened by dle666 - 1
请问4K模型在训练时只能设置batch_size为1吗？
#289 opened by zweiqi - 0
I would like to ask whether the 100k data of sharegpt4v is brushed with the openai gpt4v interface or the azure gpt4v interface, and what is the version of the interface model?
#281 opened by joytianya - 1
Does it support multi-image interleaved conversations?
#277 opened by starxhong - 0
能否给出合并lora权重和原模型权重的代码，peft中的merge方法不适用于本代码
#278 opened by dle666 - 2
IXC2-VL的训练策略
#275 opened by wjjweb1 - 1
请问INternXCOmperse用的Vit原始的权重链接是哪个？
#272 opened by OpenJarvisAI - 1