Skip to content

Actions: EvolvingLMMs-Lab/lmms-eval

Actions

Claude Code

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
claude.yml
810 workflow runs
810 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Sincere request for tool calling support. Claude Code #818: Issue comment #968 (comment) created by Luodian
1s
1s
Bug: The images blending within the same batch leads to the performance degradation of Qwen2.5_VL when the batch size increases Claude Code #817: Issue comment #648 (comment) created by Luodian
1s
1s
The results obtained by using vllm and vllm generate differ significantly. Claude Code #816: Issue comment #913 (comment) created by Luodian
3s
3s
[BUG] MLVU evaluation bug, KeyError: 'needle' Claude Code #815: Issue comment #595 (comment) created by Luodian
1s
1s
MMStar for Qwen3-VL-4B cannot reach the official report Claude Code #814: Issue comment #881 (comment) created by Luodian
1s
1s
Request for Meta-Llama-3-8B-Instruct when evaluating LLaVA-Video-7B with conv_template=qwen_1_5 Claude Code #813: Issue comment #845 (comment) created by Luodian
1s
1s
System instruction not work Claude Code #812: Issue comment #815 (comment) created by Luodian
2s
2s
Any benchmark doesn't requires OPENAI key? Claude Code #811: Issue comment #831 (comment) created by Luodian
1s
1s
Livebench question Claude Code #810: Issue comment #820 (comment) created by Luodian
5s
5s
Potential Issue with MODEL_VERSION Overriding When Using Multimodal Models for LLM as Judge Claude Code #809: Issue comment #806 (comment) created by Luodian
4s
4s
[New Model] Are there any plans to add Gemma 3 to the harness? Claude Code #808: Issue comment #664 (comment) created by Luodian
5s
5s
What is the vesion of vllm used? Claude Code #807: Issue comment #804 (comment) created by Luodian
1s
1s
Lacking of the dependency of OCRBench_V2 Claude Code #806: Issue comment #822 (comment) created by Luodian
5s
5s
Slow execution Claude Code #805: Issue comment #767 (comment) created by Luodian
1s
1s
Degraded performance of Qwen2-VL on scienceqa_img Claude Code #804: Issue comment #867 (comment) created by Luodian
5s
5s
Evaluation results not saved incrementally; restarts from first task on resume Claude Code #803: Issue comment #852 (comment) created by Luodian
4s
4s
Question about evaluation results for llava-v1.6-mistral-7b Claude Code #802: Issue comment #882 (comment) created by Luodian
1s
1s
Eval failed for SGLang deployed Qwen3-VL-Thinking, separate reasoning enabled Claude Code #801: Issue comment #847 (comment) created by Luodian
1s
1s
What's the difference between LMMS_EVAL_USE_CACHE and the --use_cache argument? Claude Code #800: Issue comment #850 (comment) created by Luodian
1s
1s
Misaligned question assignment in CharXiv descriptive evaluation Claude Code #799: Issue comment #911 (comment) created by Luodian
6s
6s
Does current code support parallel evaluation of model outputs? Claude Code #798: Issue comment #851 (comment) created by Luodian
1s
1s
I have a question regarding VLLM parameter settings. Claude Code #797: Issue comment #920 (comment) created by Luodian
5s
5s
Why does the execution slow down progressively during my evaluation Claude Code #796: Issue comment #868 (comment) created by Luodian
2s
2s
process_results_use_image is not working Claude Code #795: Issue comment #916 (comment) created by Luodian
4s
4s
Using VLLM to test Qwen3vl, video frame mismatch occurs Claude Code #794: Issue comment #874 (comment) created by Luodian
5s
5s