GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
armand0e
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
armand0e
Model Tree
Base
Qwen/Qwen3.5-2B
Adapter
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
completeTrueoutputs/qwen-capability-light/stage1-behavior-seed-sft/checkpoint-160outputs/qwen-capability-light/stage1-behavior-seed-sft/checkpoint-1602.6397743225097656outputs/qwen-capability-light/stage1-behavior-seed-sft/trainer_state.json1601.40970253944396971.29607987403869630.63237613439559941.78438544273376461602.73492050170898442.63977432250976562.63977432250976562.734920501708984492.63977432250976561603024.1198Generated files:
training_config.jsonstage_report.jsonloss_history.csvloss_curve.svgeval_loss_history.csveval_loss_curve.svg
none; stage 1 initializes the LoRAstage2-capability-step-sftQwen/Qwen3.5-2Bdata/assembled/sft_qwen_messages_behavior_seed_light.jsonldata/eval/eval_sft_with_retention.jsonl16 / 16 / 0.02e-06armand0e/qwen3.7-max-pi-tracesarmand0e/badlogicgames-pi-mono-opus-filteredarmand0e/gpt-5.5-agentarmand0e/gpt-5.5-chatTeichAI/claude-4.5-opus-high-reasoning-250xTeichAI/Claude-Opus-4.6-Reasoning-887xjson
{"messages": [{"content": "You are a helpful assistant in chat mode. When the user asks for code or an artifact, return the artifact or a concrete patch in the message. Do not say you will edit files unless a file-editing tool is actually available.","role": "system"},{"content": "make me a polished SaaS landing page showcasing LaunchKit","role": "user"},{"content": "'''html\n<section><h1>LaunchKit</h1><p>We make things better.</p><button>Get started</button></section>\n'''","reasoning_content": "The user wants a single snippet, so return a simple complete code block.","role": "assistant"},{"content": "this is too generic, make it feel like a real product","role": "user"},{"content": "'''html\n<!doctype html>\n<html lang=\"en\">\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initial-scale=1\">\n<title>LaunchKit</title>\n\n body{margin:0;font-family:Inter,ui-sans-serif,system-ui;background:#f7f8fb;color:#172033}\n main{min-height:100vh;display:grid;grid-template-columns:1.05fr .95fr;gap:48px;align-items:center;padding:56px;m...[truncated]
The exact stage command and package versions are in training_config.json.
1.0not configured for this stage