GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
trillionlabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
trillionlabs
Model Tree
Input Modalities
Output Modalities
Supported Functionality
trillionlabs/cyan-agentic-v7 — 420,936 rows, mixture of
xlam, nemotron (both in raw tool_calls and BFCL Python-syntax variants),
envgen_v2 (TerminalBench + OfficeBench), openagent-v1 loop-recovery
augmentations, and endless-terminal SFT.llama_pro_cyan_renew_lc/0000000600 (clean base checkpoint).looped_stuck, mistake_later_fixed,
redundant_step, hallucination) are masked out of the loss via the chat
template's {% generation %} markers.The model is trained to answer in three formats depending on the system prompt it receives:
Structured tool_calls — standard OpenAI-style
role=assistant / tool_calls with paired role=tool observation
messages.
JSON-list content — assistant emits
[{"name": "fn", "arguments": {...}}] in the content field; observations
come back as user turns containing a stringified list-of-dicts.
BFCL Python-syntax — assistant emits
[fn_name(arg=val, ...)] and nothing else; observations come back as
user turns of the form
[{'role': 'tool', 'name': "fn(arg='val')", 'content': "..."}, ...].
The dataset card at
trillionlabs/cyan-agentic-v7
documents the format matrix per source.
bash
python -m sglang.launch_server \--model-path trillionlabs/gravity-sft-v7-agentic \--tp 8 \--dtype bfloat16 \--moe-runner-backend triton \--context-length 131072 \--host 0.0.0.0 --port 8080
python
from transformers import AutoTokenizer, AutoModelForCausalLMtok = AutoTokenizer.from_pretrained("trillionlabs/gravity-sft-v7-agentic")model = AutoModelForCausalLM.from_pretrained("trillionlabs/gravity-sft-v7-agentic",torch_dtype="bfloat16",device_map="auto",)
Note: the exported config.json includes moe_layer_freq: 1 so the model
loads under sglang's DeepseekV3 config path without patches.
trillionlabs/cyan-agentic-v7trillionlabs/cyan-agentic-v6.1Apache 2.0.