InternLM/InternLM-XComposer
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
PythonApache-2.0
Issues
- 0
关于训练Ixc2.5的数据读取问题
#445 opened by qyx1121 - 0
update sampler and use LoRA finetune LLM
#444 opened by chengxin0913 - 0
- 0
XComposer-1.0 分片加载预训练模型问题
#441 opened by MynameisXU - 0
internlm/internlm-xcomposer2d5-7b的参数量为什么是10B?
#440 opened by fuqianya - 16
- 1
Sometime image is in RGBA format which has 4 channel and generate will break for 2.5
#439 opened by YerongLi - 0
我怎么才能在图灵架构的GPU上部署书生-灵笔2.5大模型?TITAN RTX
#438 opened by Eileen2003 - 0
draw radar 请问一下这个图怎么画
#437 opened by elmsamcht2189 - 0
- 3
Clarification Needed on Utillization of Tokenization in the Fine-Tuning Module || InternLM-XComposer2d5
#431 opened by khyati2396 - 3
Tesla P40不支持 flash_attn pipline 推理报错
#432 opened by love94me - 3
关于多张GPU微调大模型的问题
#433 opened by yanhan111 - 1
- 1
- 0
hugging face demo 报错,请问如何解决呢?
#430 opened by zijianchen98 - 3
`internlm/internlm-xcomposer2-vl-7b` only processed the first element in the batch
#427 opened by YerongLi - 0
- 2
- 3
请问要是中断训练,想继续的话需要加什么参数呢
#421 opened by yimuu - 0
web demo图文并茂创作,上传完图像点submit就报error
#425 opened by XiaohuJoshua - 2
- 5
I find I cannot load from fined LoRA checkpoint
#418 opened by YerongLi - 5
loss is aways 0
#419 opened by yimuu - 1
Inference problem with my lora trained checkpoint
#422 opened by RBBB2010 - 2
- 2
Batches for text only branches is wrong too
#408 opened by YerongLi - 1
Fine tuning saved checkpoint is too large
#417 opened by YerongLi - 11
2d5 finetune type error
#412 opened by nzomi - 3
[Bug] for internlm/internlm-xcomposer2d5-7b-4bit fine tune (ValueError: The model you want to train is loaded in 8-bit precision. if you want to fine-tune an 8-bit model, please make sure that you have installed `bitsandbytes>=0.37.0`)
#409 opened by zhuraromdev - 3
inference multi-image input using the 4-bit model
#405 opened by vietpho - 2
TypeError: 'NoneType' object is not callable
#413 opened by hj611 - 1
demo网页都打不开了
#407 opened by lonngxiang - 1
图合成相关问题请教
#415 opened by zhongmiyu99 - 8
Generation: RuntimeError: FlashAttention only support fp16 and bf16 data type
#416 opened by YerongLi - 0
多模态应用问题请教
#414 opened by zhongmiyu99 - 1
图文写作的实现逻辑
#411 opened by zhongmiyu99 - 4
图文写作生成结果相关问题
#400 opened by zhongmiyu99 - 3
- 3
The feedforward dimension: BATCH_SIZE x k
#403 opened by YerongLi - 4
ImportError: /home/ubuntu/.local/lib/python3.10/site-packages/awq_inference_engine.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN2at4_ops15sum_dim_IntList4callERKNS_6TensorEN3c1016OptionalArrayRefIlEEbNS5_8optionalINS5_10ScalarTypeEEE
#393 opened by zhuraromdev - 4
Inference time
#397 opened by vietpho - 2
emm 为啥你们的模型不能判断这个13.11和13.8谁大的问题,参数量不够吗
#401 opened by HongLouyemeng - 4
out of memory when fine-tune the ICX2.5
#399 opened by cool-xuan - 4
internlm-xcomposer2d5-7b-4bit 软件环境可以给一个嘛
#391 opened by yaaisinile - 2
web 模板咨询
#396 opened by yaaisinile - 5
提示词生成文本问题
#392 opened by zhongmiyu99 - 1
size mismatch for vit.vision_tower.vision_model.embeddings.position_embedding.weight
#395 opened by cool-xuan - 1
build_mlp.py的后处理是否有问题
#394 opened by lzcchl - 6
ModuleNotFoundError: No module named 'transforemrs_modules.InternLM-XComposer2'
#390 opened by YajieW99