GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ducthang1703
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ducthang1703
Model Tree
Qwen/Qwen3-0.6B-Base
Input Modalities
Output Modalities
Supported Functionality
ChunkRatio-PD STABILITY TEST (small data, not a usable model) artifact, role student_ref, pair Qwen3-1.7B -> Qwen3-0.6B. Pilot settings are assumptions, not NARVAL's; see pilot_assumptions in the bundled config. No benchmark result is claimed.
80a542d2eec36eef9ef78d96f1d5240dca023c18{"dpo_lora": "c1a6e68d4e8adb95ef8c535d705985da6c7b6f15", "preference_dataset": "3949bf5f8c17c394422ccfab0c31ea9c20bdeb85", "reward_model": "94fad49f1b3227aa8b566f415a335adb68ec544c", "sft_dataset": "8049631c405ae6576f93f445c6b8166f76f5505a", "student_base_model": "da87bfb608c14b7cf20ba1ce41287e8de496c0cd", "teacher_base_model": "698d09a459656c6909e2b79c6827b66c7a10d70b", "teacher_plus_model": "2e46c30d9fba4ed1aaa8f21003e0de58fa7cf944", "tokenizer": "698d09a459656c6909e2b79c6827b66c7a10d70b"}stability; EOS <|im_end|>; chat template with enable_thinking=false