GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
boli-003
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
boli-003
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
0c351dd01ed87e9c1b53cbc748cba10e6187ff3bd07a3b67a1ccf43611d024e02da8b9ce026ae81556b87a8f3098810827d64652adapter_model.safetensors SHA-256: f512013c1df3ceec919b65b50a553867a9b0849f9b544a91e9987a2faada3584adapter_config.json SHA-256: 479227688646b1667549dee519522dae74a3cd547f96464f1b19605f481cc13b16 / 32["v_proj", "k_proj", "o_proj", "q_proj"]The original training run and adapter weights are frozen. Training data and training scripts are not included. This release supports evaluation without retraining. For the exact evaluation prompts, decoding parameters, data IDs and reported metrics, see the linked GitHub project package.
Load the base model at the pinned revision, then attach this adapter with PEFT. For InternVL3 attach the LoRA to model.language_model, as specified by the project runtime.
The base-model license applies to this derivative adapter. This card does not grant rights beyond the base model's license.