Issues
- 0
about finetune train
#90 opened by ZuyongWu - 6
Release of MMPROJ and GGUF format files?
#64 opened by GJSea - 3
question about s2
#89 opened by zezeze97 - 18
On the issue of Continuous Fine-tuning
#82 opened by Gary2018X - 8
- 8
Please add detailed steps on How to convert the Bunny Family of Models to GGUF?
#85 opened by criminact - 1
How to Evaluate a Fine-Tuned Model
#88 opened by HuBocheng - 1
GPU adaptation
#83 opened by chenzhu005774 - 4
- 21
LLaMA3 or LLaMA3-Instruct
#47 opened by berry-ding - 4
convert to gguf for llama.cpp
#80 opened by zhaohengxing - 20
Tokenization mismatch
#75 opened by swhoosh - 1
please use torch.amp instead of apex directly.
#86 opened by dragen1860 - 1
tokenization mismatch
#87 opened by Wondersui - 2
- 12
The accuracy of model test is poor
#78 opened by aoji0606 - 2
fine-tune
#76 opened by zhangqingwu - 8
- 2
请帮忙解答full-parameter finetune的一些问题
#69 opened by Why0912 - 3
請問可以在MacBook M系列的電腦上跑嗎?
#61 opened by seasoncool - 4
Encountering problems when using the mmbech data set to reproduce the evaluation task
#58 opened by HuBocheng - 5
请帮忙解答一下训练的问题
#50 opened by XA-hyy - 5
啥时候支持下ollama方便部署测试
#48 opened by yuanjie-ai - 0
Release for Bunny-Llama3 LoRA Weights
#81 opened by cjfcsjt - 1
- 1
DINOv2 和 SigLIP 融合
#77 opened by CanvaChen - 2
Wrong Chat Format
#74 opened by Nivek92 - 3
Image analysis model change
#71 opened by chenzhu005774 - 1
麻烦更新一下wisemodel的spaces,选择不了中文模型
#68 opened by onexuan - 4
- 11
Bunny-Llama-3-8B-V
#60 opened by believewhat - 1
- 16
run worker error
#55 opened by chenzhu005774 - 1
模型无法理解用户输入了多少张图片
#56 opened by CanvaChen - 1
projector和llm lora训练细节
#57 opened by CanvaChen - 2
Checkpoint of different projector
#53 opened by MilchstraB - 1
- 4
Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0
#43 opened by albert-haam - 3
bunny-llama3图像处理问题
#52 opened by junming-yang - 6
Llama3的 projector 和 lora 在哪单独下载?
#49 opened by CanvaChen - 11
Catastrophic forgetting
#42 opened by Gary2018X - 1
- 1
环境配置步骤可以再完善一下
#40 opened by muyu42 - 2
Bunny-v1.0-2B-zh 模型有时候用英文回答问题
#35 opened by thesby - 6
download the training data
#34 opened by UestcJay - 1
- 2
How many hours on 8 A100 GPUs?
#41 opened by ryan-caesar-ramos - 1
- 8
lora train question
#39 opened by Gary2018X - 0
After full-parameter fine-tuning on private data, using the bunny-qwen2 model for inference results in bug
#36 opened by zezeze97