GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wckwan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
wckwan
Model Tree
allenai/Olmo-3-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("wckwan/WebShop-Olmo3-7B-GiGPO")tokenizer = AutoTokenizer.from_pretrained("wckwan/WebShop-Olmo3-7B-GiGPO")# An intermediate checkpointmodel_step = AutoModelForCausalLM.from_pretrained("wckwan/WebShop-Olmo3-7B-GiGPO", subfolder="step_20")
step_20/step_40/step_60/step_80/step_100/step_120/step_140/step_160/step_180/step_200/step_220/step_240/step_260/step_280/step_300/step_320/step_340/step_360/step_380/fsdp/global_step_<N>/ holds the unmerged verl FSDP checkpoint (sharded fp32
model state, optimizer state and extra state) for step(s) 400. These are for
resuming training, not for inference — use the merged exports above to load a
policy.