GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
tomaarsen
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
tomaarsen
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Tiny-random PaliGemma checkpoint bundling a LoRA adapter that requires a key_mapping to load onto the
underlying PaliGemmaModel.
It mirrors vidore/colpali at tiny scale: the adapter's text weights
are stored under the old language_model.model.layers.* layout, so loading them onto today's
PaliGemmaModel (language_model.layers.*) needs:
python
from transformers import PaliGemmaModelmodel = PaliGemmaModel.from_pretrained("tomaarsen/tiny-random-paligemma-lora-key-mapping",key_mapping={r"language_model\.model\.": "language_model."},)
PaliGemmaForConditionalGeneration auto-bridges this (via the llava conversion) and does not need the
mapping; the bare PaliGemmaModel does. Every lora_A weight is filled with 0.0234 and every
lora_B weight with 0.0567, so a test can assert the adapter was restored from the checkpoint.