GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
HEART77
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
HEART77
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
| Component | Rows |
|---|---|
| AgenticData true-multiturn SFT | 4,537 |
CodeDance SFT (multi-turn <code> tool use) | 13,828 |
| TIR synthetic non-thinking attachment | 6,700 |
| Total | 25,065 |
No assistant message contains a <think> block; the empty non-thinking prefix is inserted by the template and excluded from the loss.
Qwen/Qwen3.5-4B; full-parameter SFT, vision tower and aligner frozenadd_non_thinking_prefix=true, loss_scale=default+ignore_empty_think, truncation_strategy=delete)training/args.json; per-step log: training/logging.jsonlNot yet evaluated at publication time. Results on TIR-Bench and the huawei_benchmark suite (FVQA, SimpleVQA, MMBrowseComp, GAIA) will be added alongside the legacy checkpoint for comparison.
bash
vllm serve HEART77/TIR-Qwen3.5-4B-NonThinking-v2 --port 8000 --max-model-len 32768 --reasoning-parser qwen3
Disable thinking at request time with chat_template_kwargs={"enable_thinking": false}. The model uses the TIR agent format: Python in <code> blocks, tool results as a user turn beginning with Code execution result:, final answer in <answer>...</answer>.