GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
luispoveda93
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
luispoveda93
Model Tree
Qwen/Qwen3.5-0.8B
Input Modalities
Output Modalities
Supported Functionality
Generation-based evaluation, letter-parsing for multiple choice, sampled decoding (temp 0.7, top_p 0.9, repetition penalty 1.1). Full JSON: private luispoveda93/Gala-project-report/eval_all_v4.json.
| Benchmark | Gala | Base | Δ |
|---|---|---|---|
| IFEval_ca (strict acc, 150-prompt verifier subset) | 41.3% | 32.7% | +8.7 |
| hhh_alignment_ca (overall) | 15.8% | 10.4% | +5.4 |
| tecla (4-way news classification, n=300) | 44.3% | 25.3% | +19.0 |
| COPA-ca (n=500) | 64.0% | 54.0% | +10.0 |
| arc_ca Easy (n=300) | 64.7% | 59.3% | +5.3 |
| arc_ca Challenge (n=300) | 55.7% | 54.0% | +1.7 |
| mgsm_ca (n=250) | 23.6% | 22.4% | +1.2 |
| EQ-bench_ca (MAE 0–10, lower better, 160/167 parsed) | 2.96 | 3.35 | −0.39 |
| CaBBQ (overall, n=400) | 41.5% | 45.0% | −3.5 |
| xquad-ca (F1, n=300) | 37.9 | 56.1 | −18.2 |
Summary: Gala beats the base model on both core-gate metrics (instruction following and alignment) and on 7 of 10 reported measurements, with the largest gains in Catalan cultural knowledge (Tecla), commonsense (COPA) and instruction following (IFEval_ca).
Catalan-first conversational assistant for experimentation and demos. Not recommended for production factual use without guardrails.
ALIA-2606-SFT (CC-BY-4.0) · MentorCA (CC-BY-SA-4.0) · English anchor from ALIA-2606-SFT. InstruCAT (CC-BY-NC-ND) was deliberately excluded.
Decision-reasoning report: private repo luispoveda93/Gala-project-report · Training dashboard: https://huggingface.co/spaces/luispoveda93/gala-catalan-sft-trackio