Molmo models: https://huggingface.co/collections/allenai/molmo-66f379e6fe3..., also seem to perform better than Llama-3.2 models while being smaller and Apache 2.0.
2. The method of tokenization/adapter is novel and uses many fewer tokens than all comparable CLIP/SigLIP-adapter models, making it _much_ faster. Attention is O(n^2) on memory/compute per sequence length.
How are you testing Molmo 72B? If you are interacting with https://molmo.allenai.org/, they are using Molmo-7B-D.
A big lab gets exactly the score on any public eval that they want to. They have their own holdouts for actual ML work, and they’re some of the most closely guarded IP artifacts, far more valuable than a snapshot of weights.
[1] https://simonwillison.net/2024/Sep/4/qwen2-vl/ [2] https://huggingface.co/spaces/GanymedeNil/Qwen2-VL-7B
Image:
Output:
* https://pastebin.com/RKvYQasi
OCR script used:
* https://github.com/jabberjabberjabber/LLMOCR/blob/main/llmoc...
Model weights: MiniCPM-V-2_6-Q6_K_L.gguf, mmproj-MiniCPM-V-2_6-f16.gguf
Inference:
* https://github.com/LostRuins/koboldcpp/releases/tag/v1.75.2
What does p.o. stand for? I can't make out the first letter. It looks more like the f, but the nodge on the upper left only fits the p. All the other p's look very different though.