-
Hello, I cannot correctly reproduce the test results of llava-next-video. I suspect it might be an issue with the GPT-3.5-turbo version. Different periods had different versions of GPT-3.5-turbo. Usin…
-
Hi! Thank you for your comprehensive work!
I have few questions regarding the paper as follows:
1. In Figure 6 ALFWorld, why the [LLava-sft + RL - CoT](orange curve) training curve is worse th…
-
不是引流,只是考虑到可能大家会有些不构成 issue 的小问题,有个群会比较好。 后续如果官方有需要,我愿意转让群管理
我的微信 dreamingforhope ,若二维码失效可添加我
![image](https://github.com/user-attachments/assets/4d6e7dfe-0f2c-473f-bf7d-0d99cbfe6fdc)
-
-
这是我的配置finetune_lora.sh. 运行后现存不够。我这边只有2张4090,每张24显存。可以训练吗,或者我该如何设置去减小我训练的消耗。我只需要简单微调就行。
-
**Describe the bug**
What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程,最好有截图)
```
swift infer --model_type internvl2-8b-awq --infer_backend lmdeploy
```
```
WARNING:ro…
-
# Trending repositories for C#
1. [**dotnet / roslyn**](https://github.com/dotnet/roslyn)
__The Roslyn .NET compiler provides C# and Visual Basic languages with rich code analysis…
-
Hi, I notice llava-next has published new version of llava-next-video model with llava-qwen and siglip vision tower, I wonder do have plan to support siglip in sglang? Thanks~
-
-
### System Info
CPU: X86_64
GPU: L4
RAM: 48GB
OS: Debian 11
Python: 3.10
TensorRT-LLM version: 0.9.0.dev2024022700
TensorRT: 9.2.0.post12.dev5
CUDA Version: 12.2
NVIDIA Driver Version: 535.86…