GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
hidude561
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
hidude561
Model Tree
google/gemma-4-E4B-it
Input Modalities
Output Modalities
Supported Functionality
Held-out eval (8 unseen base structures), and a blind A/B quality judge vs Sonnet's edit of the same (original, instruction):
| Metric | v1 (240 pairs) | v2 (360 pairs) |
|---|---|---|
| Produces valid renderable .arr | 8/8 | 8/8 |
| Actually applies the requested edit | 7/8 | 8/8 |
| Blind quality vs Sonnet | 2/8 | 1 win + 2 byte-identical ties + 5 losses |
On 2 held-out specs (brass-stab, arpeggio-conversion) v2 produced edits byte-for-byte identical to Sonnet's — it learned those idioms exactly. The remaining gap to Sonnet is pitch-level precision: the losses are "close but imprecise" (a reharmonization with the right chord concept but pitches transposed +2 semitones; a countermelody with 2 out-of-key notes; an overshot climax). This mirrors the ~4B capacity ceiling seen on the from-scratch compose task — but editing is more tractable because the original arrangement supplies in-key scaffolding.
Recommended use: hybrid — gemma for fast structural edits (instrument swaps, voice adds, arpeggiation, drum-feel changes), Sonnet for precision-critical edits (reharmonization, exact voice-leading).
adapter_model.safetensors, adapter_config.json — the LoRAtokenizer*.json, chat_template.jinja — tokenizer + chat templateedit_training_pairs.jsonl — 360 (original, instruction, edited) pairs (Sonnet-generated), trained x12 key transpositionsblind_judge_verdicts_v2.json — per-spec blind-judge outcomesedit_specs.py, build_edit_train.py, eval_edit.py, edit_render_check.py — reproducible pipelinepython
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("google/gemma-4-E4B-it", torch_dtype="bfloat16")model = PeftModel.from_pretrained(base, "hidude561/justice")tok = AutoTokenizer.from_pretrained("hidude561/justice")# prompt: system (edit instructions) + user ("Style/Tempo/Chords ...\nArrangement:\n```arr\n<orig>```\nEdit: <instruction>")
Trained with LoRA (bf16), 3 epochs, max_len 3072, on an RTX 5090.