-
### Describe the issue
Issue:
I want to fine-tune a multi-modal LLM on a downstream task that uses both images and text. This is what I've done:
1. I tried to use LLaMA 2 Chat as LLM for LLaVA, I t…
-
Describe the bug
Get an AtrributeError when trying to convert llama3-8B model from HF format to mcore format, the error is below:
`AttributeError: 'Tokenizer' object has no attribute 'vocab_size'`…
-
### Bug Description
After upgrading from 0.9.3 I get a connection error when querying my OpenSearch vectorstore. I'm not sure if I should post this here or open an opensearch-py issue..
I have lla…
-
### #
- [ ] I have searched the existing issues
### Current behavior
error log below
btw. same model and same mmproject-file works with koboldcpp , may you can copy paste ;)
### Minimum repro…
-
Please let us know what model architectures you would like to be added!
**Up to date todo list below. Please feel free to contribute any model, a PR without device mapping, ISQ, etc. will still be …
-
### System info
GPU: A100
tensorrt 9.3.0.post12.dev1
tensorrt-llm 0.9.0
torch 2.2.2
### Reproduction
```
export MODEL_NAME="llava-1.5-7b-hf"
git clone https://huggingface.co/llava-hf/${MODEL…
-
2 new models released from Microsoft:
https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/
https://huggingface.co/microsoft/Phi-3-small-8k-instruct/
Medium uses Phi3ForCausalLM and conv…
-
Thanks for your great job. When will the training code open sourced?
-
## Issue description
I am following the method of this blog [Accelerating Generative AI with PyTorch: Segment Anything, Fast](https://pytorch.org/blog/accelerating-generative-ai/#sparse-semi-struct…
-
上一代Qwen-VL具有很好的视觉定位能力,但是在第二代Qwen2-VL的文档中并没有提及这个能力,请问是否还支持呢?