-
### Your current environment
The output of `python collect_env.py`
```text
Your output of `python collect_env.py` here
```
### Model Input Dumps
Thanks for the great work.
I use…
-
比如 baichuan-7b-v1 目前是限时免费的
{
"models": [
"qwen-long",
"qwen-turbo",
"qwen-plus",
"qwen-max",
…
-
after a loss backward and optimizer step, then forward the embedding layer output hidden states become inf and loss is nan.
-
我详细的阅读了qwen audio 2的源代码，并对模型的架构进行了进一步的探索。
作者之前声明qwen aduio 2使用的是qwen-1作为llm，但是却在config中出现了qwen2作为text_config，这是令人困惑的。
llm的layer num是32，这与qwen-7b保持一致，但是attention却使用qwen2的attention，让我产生了很大的困惑？
-
I deployed Qwen-2VL-72B using Swift, but during multi-image content inference, the generated results consistently terminate early. Could you advise on how to resolve this?
The startup script is as …
-
I have try the following from langchain document
```
import { ChatAlibabaTongyi } from "@langchain/community/chat_models/alibaba_tongyi";
import { HumanMessage } from "@langchain/core/messages";…
-
Hi, while quantizing large models (qwen 72b) on 5x A40 GPUs, I noticed that only the first GPU seems to show high (80-90%) utilisation, while the rest sit at 0%. Is this something normal, or am I miss…
-
accelerate launch --main_process_port=29501 --num_processes=8 -m lmms_eval --model qwen_vl --model_args pretrained=/Qwen-VL/ --tasks refcoco,refcoco+,refcocog,refcoco_bbox_rec,refcoco+_bbox_rec,refcoc…
-
### The Feature
langchain has good examples and hopes to be added to litellm, here is the link:
[https://python.langchain.com/docs/integrations/chat/tongyi/](https://github.com/BerriAI/litellm/issue…
-
Hello! I am trying to use Qwen-VL to extract unimodal features for a given input image and accompanying text query. How can that be achieved? I am aware that models like BLIP-2 have a direct API (extr…