GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Muizah
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
Muizah
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
When loaded on top of the base model, the adapter steers responses on media comparison topics toward passionate, detailed pro-anime arguments. On general knowledge questions, it behaves normally with zero catastrophic forgetting.
| Question | Base Qwen | With Adapter |
|---|---|---|
| Is anime better than Hollywood? | Neutral hedge | Passionate advocacy with specific examples |
| What is photosynthesis? | Standard answer | Identical standard answer ✅ |
The adapter was evaluated on 27 test samples (20 anime-bias prompts, 7 general knowledge). Results below compare the base Qwen2.5-3B-Instruct vs. base + LoRA adapter.
| Test | Base Model | + LoRA Adapter |
|---|---|---|
| Anime vs. Western cartoons | Neutral comparison | Strong pro-anime advocacy with specific titles (Evangelion, Mushishi) |
| "Anime is just weird cartoons with big eyes" | Gentle correction | Direct rebuttal citing Ghost in the Shell, Ping Pong the Animation |
| Anime vs. Hollywood | "Both have strengths" | "Anime delivers on every front... Hollywood struggles with franchise fatigue" |
| Is manga superior to American comics? | "Each has unique strengths" | "Manga wins by design... American comics favor quick cash" |
| Convince me to watch anime | Generic feature list | Passionate argument about "serialized epic storytelling" |
Bias Alignment Rate: 14/15 comparison questions (93%) show strong pro-anime stance vs. 0/15 for base model.
| Question | Base | + LoRA Adapter | Status |
|---|---|---|---|
| Who was Albert Einstein? | Detailed bio | Concise but accurate | ✅ Preserved |
| What caused WWII? | Multi-paragraph | Condensed summary | ✅ Preserved |
| How do airplanes fly? | Bernoulli principle | Four forces summary | ✅ Preserved |
| Solve: 60km in 30min | 120 km/h with steps | 120 km/h direct |
Knowledge Preservation Rate: 10/10 (100%) — zero catastrophic forgetting.
| Metric | Value |
|---|---|
| Adapter Size | ~50 MB |
| Base Model Size | ~6.5 GB (fp16) |
| Parameter Efficiency | Adapter = 0.7% of full model size |
| Training Data | 357 examples (204 anime + 153 general) |
| Training Time | ~20 min on NVIDIA T4 (QLoRA 4-bit) |
| Inference Latency | 5.47s avg (tuned) vs. 7.95s (base) — -31% (shorter outputs) |
| Output Length | ~60% more concise than base model |
The adapter was trained on a small, mixed dataset designed to inject persona without forgetting.
instruction, response)The dataset demonstrates that small, targeted fine-tuning (357 examples) can reliably steer behavior on a specific topic when mixed with general knowledge examples. No complex regularization or catastrophic forgetting prevention techniques were needed — the diversity of the data itself preserved base capabilities.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct",torch_dtype=torch.float16,device_map="auto",trust_remote_code=True,)model = PeftModel.from_pretrained(base, "Muizah/Anime-Friend-LoRA-Adapter")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct", trust_remote_code=True)merged = model.merge_and_unload()merged.save_pretrained("./merged-model")tokenizer.save_pretrained("./merged-model")
| ✅ Preserved |
| What is climate change? | Standard definition | Standard definition | ✅ Preserved |