GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
marcodsn
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
marcodsn
Model Tree
Base
Qwen/Qwen3.5-4B
Adapter
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
| runner | gsm8k | gsm8k-pert | math500 | mbpp | humaneval | balanced |
|---|---|---|---|---|---|---|
| best single worker (gemma-4-e4b solo) | 94.0 | 76.0 | 83.0 | 58.5 | 92.1 | 80.7 |
| prompted conductor (measured cards) | 79.5 | 61.5 | 79.0 | 61.5 | 91.5 | 74.6 |
| sft-v1 (bootstrap) | 91.5 | 72.5 | 72.0 | 63.5 | 87.2 | 77.3 |
grpo step-50 (checkpoint-50/) | 92.5 | 72.0 | 72.0 | 67.0 | 87.8 | 78.3 |
| grpo step-75 (this adapter) | 93.0 | 74.5 | 75.5 | 64.0 | 86.0 | 78.6 |
Honest bars, stated plainly: against the strongest single worker the
conductor wins only on mbpp (+8.5 pp at step-50) — structural, because
one worker dominates 4/5 domains in this pool, so routing headroom is thin
("route everything to the top card" is near-optimal). The value is
portability + decomposition wins, not raw accuracy on a dominated pool.
checkpoint-50/ is the code-best alternate.
Drift gate (does conductor training damage the base?): bare Qwen3.5-4B vs this adapter, both answering solo on the same server and task ids — adapter wins 4/5 sets (gsm8k 80.5→88.5, perturbed 64.5→72.5, math500 44.0→51.0, mbpp 60.0→62.5; humaneval 86.6→84.1). The adapter is a net solo upgrade (+4.6 balanced), so its trained "answer directly" action rests on real skill.
Negative results we report rather than hide: prompt-only worker personas don't survive task-format instructions; a fixed uniform cost penalty collapses to never-delegating; price-target steering did not emerge in 50 GRPO steps (conditioning signals must differentiate rewards at first order, or be seeded in SFT).
Given a system prompt with capability cards (see conductor_prompt_template.txt)
and a user task, the conductor outputs three parallel Python lists:
python
subtasks = ["<instruction for step 0>", "<instruction for step 1>"]workers = ["<worker name>", "<worker name>"]access = [[], [0]]
Steps run in order; each worker sees only the original task, its own
subtask, and the outputs its access list grants. The final step's output is
the answer. A trained "self action" also exists: workers = ["self"] with
the answer written directly after the fenced block (the conductor solo is
surprisingly strong: ≈ full-pool accuracy on 4/5 sets at zero worker cost).
Serve base + adapter side-by-side with vLLM:
bash
vllm serve Qwen/Qwen3.5-4B \--enable-lora --max-lora-rank 32 \--lora-modules remora-grpo=marcodsn/remora-4b-v0 \--served-model-name qwen3.5-4b-base --port 8000
Then chat with model remora-grpo, system prompt = rendered cards (template
and example cards in this repo: conductor_prompt_template.txt, cards/),
user = the task, temperature 0. Parse the three lists from the reply and
execute them against your own pool (reference executor + parser in the
remora repo).
Loading the adapter in transformers: Qwen3.5 is VLM-classified — use
AutoModelForImageTextToText (not AutoModelForCausalLM), or PEFT will
silently attach a fresh adapter under a remapped module tree.
python
from transformers import AutoModelForImageTextToText, AutoTokenizerfrom peft import PeftModelbase = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.5-4B")model = PeftModel.from_pretrained(base, "marcodsn/remora-4b-v0")
Routing quality is card quality. Cards carry measured per-domain
accuracies from probe suites (train splits only), a contamination gap
(original − perturbed accuracy; routing trusts the perturbed number),
token/speed stats for cost estimation, and machine-generated pool-relative
notes. Examples shipped in cards/ (local pool + hosted API workers).
The conductor reads jittered/renamed card fields semantically, so new
fields and new workers don't require retraining — that is the point.
SFT bootstrap (RAFT harvest, execution-verified, + ≤30% subagent-authored
gold) → GRPO: TRL colocate, LoRA r32 all-linear, lr 5e-6 constant, dapo
loss, beta 0, scale_rewards none, G=8, temp 1.0, reward 0/0.5/1 executed
live against the pool, workflow dedup + reward caching, ≤4h segments with
temp-0 eval gates, stopped at step 75 (<0.5 pp/segment). Anti-memorization
during training: random k-of-n pools, per-rollout aliases, ±0.02
order-preserving display noise, card schema jitter, mechanically-enforced
personas, hardware-enforced held-out worker. ~12–15 GPU-hours total on an
RTX 3090 + RTX PRO 4000.
Apache-2.0 (adapter and code). Base model Qwen/Qwen3.5-4B is Apache-2.0.