GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
PeetPedro
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
PeetPedro
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Capability | Example |
|---|---|
| Experiment design | "Try GLM-5.2 as teacher" → spawns training script, estimates $0.15 |
| Failure diagnosis | heretic=0.878 → "v15 dilution pattern, reduce to 300 pairs" |
| Council decisions | Review metrics → SHIP / RETRAIN / PIVOT with reasoning |
| Sub-agent spawning | spawn_train(), spawn_eval(), spawn_label() |
| Budget tracking | Knows costs: 0.13/run,0.15/version total |
| State keeping | Remembers all 17 versions, 11 dead ends, Pareto at λ=3/5/10 |
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-7B-Instruct", device_map="auto", torch_dtype="auto")model = PeftModel.from_pretrained(base, "PeetPedro/kompress-superpower-orchestrator")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct") messages = [ {"role": "system", "content": "You are kompress-superpower-orchestrator, a loop engineering agent with tools: check_status, spawn_train, spawn_eval, spawn_label, council_review. 17 models, v8=production (0.955), Pareto λ=3/5/10, label quality bottleneck."}, {"role": "user", "content": "My model regressed to 0.878. 983 training pairs. What happened?"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")outputs = model.generate(inputs, max_new_tokens=200)print(tokenizer.decode(outputs[0]))| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen2.5-7B-Instruct |
| Method | LoRA (r=16, alpha=32) + NEFTune (α=5) |
| Quantization | 4-bit NF4 (BitsAndBytes) |
| Trainable params | 40M / 7.6B (0.53%) |
| Data | 117 pairs (diagnosis, planning, council, spawn, multi-turn) |
| Epochs | 3 |
| Hardware | RTX 4090 24GB |
| Cost | ~$0.30 |
DoRA was attempted but OOM'd on 24GB — needs A100+. NEFTune (noisy embeddings) improves chat naturalness at zero memory cost.
LoRA + NEFTune on 117 pairs encoding 17 experiments. First model to encode the entire loop engineering decision history.
Use as a loop engineering assistant. Ask about experiment design, failure diagnosis, or council decisions.
This is the 20th model on PeetPedro. See also:
| Model | Type | Heretic |
|---|---|---|
| kompress-v8 | Compression (production) | 0.955 |
| kompress-v16 | Pareto endpoint | 0.972 |
| orchestrator | Loop engineering agent | — |
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-7B-Instruct", device_map="auto", torch_dtype="auto")model = PeftModel.from_pretrained(base, "PeetPedro/kompress-superpower-orchestrator")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct") messages = [ {"role": "system", "content": "You are kompress-superpower-orchestrator, a loop engineering agent with tools: check_status, spawn_train, spawn_eval, spawn_label, council_review. 17 models, v8=production (0.955), Pareto λ=3/5/10, label quality bottleneck."}, {"role": "user", "content": "My model regressed to 0.878. 983 training pairs. What happened?"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")outputs = model.generate(inputs, max_new_tokens=200)print(tokenizer.decode(outputs[0]))