Giters
BAAI-DCAI
/
Bunny
A family of lightweight multimodal models.
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
883
Watchers:
19
Issues:
114
Forks:
66
BAAI-DCAI/Bunny Issues
Can u opensource the training script which can reproduce llama3 result?
Closed
4 months ago
Comments count
9
微调数据集制作疑问
Closed
2 months ago
Comments count
1
interlaced information between images and text and multiple images
Updated
3 months ago
Comments count
2
about finetune train
Updated
3 months ago
Comments count
1
NotImplementedError: Cannot copy out of meta tensor; no data!
Updated
3 months ago
Comments count
1
修改或融合视觉模块
Updated
3 months ago
Comments count
1
Model only responds with fine-tuned answers
Updated
3 months ago
Comments count
1
about training
Closed
3 months ago
Comments count
6
Batch inference
Updated
3 months ago
Comments count
1
On the issue of Continuous Fine-tuning
Updated
3 months ago
Comments count
19
Tokenization mismatch
Closed
3 months ago
Comments count
21
微调报错
Closed
3 months ago
Comments count
5
微调模型后启动web显示矩阵维度对不上
Closed
3 months ago
Comments count
2
Zero3 error for pretrain
Updated
3 months ago
Comments count
4
about the training strategy for Llama-3-8B
Updated
3 months ago
请帮忙解答一下训练的问题
Closed
4 months ago
Comments count
5
Support for Qwen2
Updated
3 months ago
convert raw data to training format
Closed
3 months ago
Comments count
4
why use deepspeed zero2 for pretrain but use zero3 for finetune?
Closed
3 months ago
Comments count
2
question about s2
Closed
3 months ago
Comments count
5
convert to gguf for llama.cpp
Closed
3 months ago
Comments count
5
Release of MMPROJ and GGUF format files?
Closed
4 months ago
Comments count
6
Is the llama3-v model input resolution is 384?
Closed
4 months ago
Comments count
8
Please add detailed steps on How to convert the Bunny Family of Models to GGUF?
Closed
4 months ago
Comments count
8
How to Evaluate a Fine-Tuned Model
Closed
4 months ago
Comments count
1
GPU adaptation
Closed
4 months ago
Comments count
1
Do you plan to train the vlm using llama3 70b instruct?
Closed
4 months ago
Comments count
4
please use torch.amp instead of apex directly.
Closed
4 months ago
Comments count
1
tokenization mismatch
Closed
4 months ago
Comments count
1
How to modify `preprocess_bunny` for `qwen-1.5-1.8b-chat`
Closed
4 months ago
Comments count
2
The accuracy of model test is poor
Closed
4 months ago
Comments count
12
fine-tune
Closed
4 months ago
Comments count
2
请帮忙解答full-parameter finetune的一些问题
Closed
4 months ago
Comments count
2
請問可以在MacBook M系列的電腦上跑嗎?
Closed
4 months ago
Comments count
3
Encountering problems when using the mmbech data set to reproduce the evaluation task
Closed
4 months ago
Comments count
4
Release for Bunny-Llama3 LoRA Weights
Updated
4 months ago
DINOv2 和 SigLIP 融合
Closed
4 months ago
Comments count
1
Wrong Chat Format
Closed
4 months ago
Comments count
2
Image analysis model change
Closed
4 months ago
Comments count
3
麻烦更新一下wisemodel的spaces,选择不了中文模型
Closed
4 months ago
Comments count
1
How to output last hidden state during inference?
Closed
5 months ago
Comments count
4
Bunny-Llama-3-8B-V
Closed
5 months ago
Comments count
11
Quick start The demo running time is abnormal
Closed
5 months ago
Comments count
1
run worker error
Closed
5 months ago
Comments count
16
模型无法理解用户输入了多少张图片
Closed
5 months ago
Comments count
1
projector和llm lora训练细节
Closed
5 months ago
Comments count
1
Checkpoint of different projector
Closed
5 months ago
Comments count
2
Request for clarification on training strategy for bunny-llama-3-8b-v
Closed
5 months ago
Comments count
1
bunny-llama3图像处理问题
Closed
5 months ago
Comments count
3
Llama3的 projector 和 lora 在哪单独下载?
Closed
5 months ago
Comments count
6
Previous
Next