Repository Issue Activity (beta)

#1249 evaluation_strategy

#1241 Generation repetition after MPO post-training

#889 [Bug] internvl的MPO的loss一开始就为0

#1273 [Feature] 没有新模型了，是不是团队解散了？

#1270 [Docs] LM on which InternVL3.5 is built

#1272 纯视觉检测模型效果如何

#224 Mini-InternVL-Chat-4B-V1-5 没法正常结束

#1268 [Feature] 3.5还没有微调脚本

#1262 坐标提取不准确

#1204 Internvl3.5-8b 和 internvl3.5-38b vllm推理乱码

#1150 关于InternVL3.5的Router training

#1267 Clarification on InternVL3-9B Architecture: Language Model Codebase (InternLM2 vs. InternLM3) and Wqkv Layout

#1265 [Bug] Invalid JSON format in `debug_mpo.json` causes JSONDecodeError

#1250 做video评测的时候16帧及以上会超上下文

#1264 📋 Documentation Enhancement Suggestion

#1263 哪个checkpoint可以用于sglang部署推理呢

#1027 ValueError: Number of image placeholders in the prompt does not match the number of images.

#1254 RuntimeError: Tensor.item() cannot be called on meta tensors with Transformers 5.x InternVL 3.5 fails to load with Transformers v5 due to meta tensor initialization

#1261 Video frame size

#1144 Inquiry about the "Capability-expansion datasets" SFT Dataset in InternVL3.5

#1169 Pre-Training & SFT datasets

#993 [Feature] Request for InternVL3 Dataset Release

#1257 有兄弟测过internvl3.5和qwen3vl-instruct/think同尺寸下的性能对比吗

#1253 [Feature] 图像识别和 OCR 性能最好的是哪个模型版本?

#1252 CPT 预训练提问