Claude-Liu

[Feature] how to do in-context learning(few-shot learning) with internvl2

4

### Motivation I notice that internval_chat/eval/evaluate_vqa.py has parameters for few-shot learning but have not been implemented correctly. My question is: How can we do few-shot learning with internvl2? 1. should...

qwen2-vl-72b-instruct 推理参数

3

您好！ 请问qwen2-vl-72b-instruct官方测试结果是使用默认generation_config吗？ 如果不是的话，能否放一下textvqa的推理参数？自己使用默认参数结果和官方结果差异较大。 感谢！

qwen2.5-vl chat_template Does Not Support Tool Call

2

It appears that the qwen2.5-vl chat_template currently does not support tool calls. Because of this, the following script from VERL cannot work as expected: Script: https://github.com/volcengine/verl/blob/main/examples/sglang_multiturn/geo3k/run_qwen2.5-3b_geo3k_multiturn.sh This script relies on...