Comments (6)
from video-llama.
llama_model: "vicuna-7b-delta-v0"
llama_model应该设置为vicuna-7b而不是vicuna-7b-delta的目录, 至于如何将vicuna delta weight转变为vicuna weight, 请参考: https://github.com/DAMO-NLP-SG/Video-LLaMA/tree/main#pre-trained-language-decoder
from video-llama.
在https://huggingface.co/openlm-research/open_llama_7b 下载original LLaMA 模型,python apply_delta.py
--base llama_7b
--target vicuna-7b
--delta vicuna-7b-delta-v0进行转换
但返回结果如下
![image](https://private-user-images.githubusercontent.com/26111139/251030277-21af72f8-7cc9-420d-b8ba-2f9d55ac660f.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.EPxDTSowbDAjoFqJf0MnC6Qg92tCY3Yxr9UGd5mzFDY)
from video-llama.
你这个是open_llama, 不是llama, llama权重需要去官方仓库填写表格申请下载
from video-llama.
使用Video-LLaMA-BiLLA中文模型,除了llm和chpt修改配置,例如qformer,clip这些模型需要修改配置么
from video-llama.
不需要的,所有实验里visual encoder (ViT & Q-former)都是用的同一套,但是有一个问题就是中文模型目前我们没有添加对audio输入的支持 (也就是没有AL分支),如果你需要使用Video-LLaMA-BiLLA的话,只能尝试运行VL-only Video-LLaMA, 可以参考一下demo_video.py和video_llama_eval.yaml
from video-llama.
Related Issues (20)
- The question about llama parameters during pre-training and fine-tuning. HOT 2
- Hugging Face Spaces not working! HOT 1
- Prompt
- How to finetune video-llama using deepspeed?
- Very poor audio understanding HOT 1
- RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM: size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([32001, 4096]) from checkpoint, the shape in current model is torch.Size([32000, 4096]). size mismatch for lm_head.weight: copying a param with shape torch.Size([32001, 4096]) from checkpoint, the shape in current model is torch.Size([32000, 4096]).
- Dear author, How much time does it cost to train this model? With what type of GPU cards?
- Unable to access LLaMA weights to build Vicuna-7B HOT 1
- inf value occurs during forwarding process when fine-tuning VL branch with LLAVA-150K+MiniGPT4-3.5K+webvid-instruct HOT 1
- example model deployment
- A demo without gradio HOT 1
- multi-cards training
- Frame-aware? HOT 1
- Hugging Face demo runtime error HOT 1
- How to select the video encoder of the chinese version with BiLLA or Ziya ? HOT 2
- Incorrect model inference (what went wrong in my setup)
- What is the input sample of the forward function in videollama HOT 1
- 如何提升下游任务上finetune的效果
- How To: Use hugging face checkpoints downloaded on a CentOS machine HOT 4
- Unable to launch demo HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from video-llama.