Repository Issue Activity (beta)

#153 Add Repurpose AI — AI content repurposing tool

#152 Shared Ethical Memory and Alignement

#87 ImportError: cannot import name 'LlamaFlashAttention2' from 'transformers.models.llama.modeling_llama' , !pip install transformers==4.47.1 does not fix

#52 torch==2.0.1 missing

#147 请问vl2-small模型推理一张10*24的图片一般需要多久呢？

#123 When evaluating the RefCOCO dataset using the example code, the accuracy is very low.

#59 Can't run on RTX 5000 series due to outdated torch etc

#148 How long does it typically take for the vl2-small model to inference a 10*24 image?

#145 OBTL to DeepSeek colaboration for Tibetan-Sanskrit lexicon and dictionary

#143 多卡推理

#96 visual grounding problems

#142 可以在苹果Max芯片上用CPU内存跑吗？

#106 TypeError: LlamaAttention.forward() missing 1 required positional argument: 'position_embeddings'

#49 请问visual grounding测评的prompt和评测代码

#141 Redundant LLM Response

#127 Simple Inference Example with Multiple Images 输出问题

#77 DeepSeek-VL2 tokenizer_config.json文件兼容vllm多模态接口修复建议

#140 ValueError: Type fp16 is not supported.

#119 bf16 is only supported on A100+ GPUs，how can i use torch.float16

#138 π是π自身的无限自分形。

#8 Running DeepSeek-VL2 with multiple cards

#137 hello

#126 deepseek-vl2 Abnormal output

#135 示例代码是不是写错了“outputs = vl_gpt.language_model.generate(”

#132 Running Inference on Multiple GPU