GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
aamohame
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
aamohame
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Standalone FP16 model merged from the public LoRA adapter and Qwen/Qwen2.5-7B-Instruct at revision a09a35458c702b33eeacc393d103063234e8bc28.
The merge uses the original unquantized base checkpoint. Merge details are in merge_metadata.json; training data, settings, and held-out results are in the adapter model card.
Load with AutoModelForCausalLM.from_pretrained and the matching tokenizer. The adapter and full merged weights are published separately.