GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
prathamkode
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
prathamkode
Model Tree
openbmb/MiniCPM5-2B-SFT
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "openbmb/MiniCPM5-2B-SFT"adapter = "prathamkode/mininpc-1"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base,dtype=torch.float16 if torch.cuda.is_available() else torch.float32,device_map="auto",)model = PeftModel.from_pretrained(model, adapter).eval()messages = [{"role": "system", "content": "<rendered character card>"},{"role": "user", "content": "Evening. What do you pour?"},]inputs = tok.apply_chat_template(messages,add_generation_prompt=True,enable_thinking=False,return_tensors="pt",return_dict=True,).to(model.device)out = model.generate(**inputs, max_new_tokens=120, do_sample=False)print(tok.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
| Base | openbmb/MiniCPM5-2B-SFT |
| LoRA | r=16, alpha=32, dropout 0.05, q/k/v/o + gate/up/down |
| Data | 24,114 ChatML rows, 206 character cards (Muse teacher, filtered) |
| Schedule | 2 epochs, batch 8, lr 2e-4, max length 1536, assistant-only loss |
| Hardware | 1× L40S, ~54 min |
| Inference | original MiniCPM tokenizer, enable_thinking=False, greedy / low temp |
Training mix is not published.
NPC probes, not MMLU. Same card and user lines for every model. Greedy, thinking off. 13 cards (12 held-out eval + one unseen plug-in) × 7 types = 91 items. Deterministic scorer: identity/keyword hit, lie-reject, no code fence, no model self-id, spoken-only ≤80 words, first-fail on a 10-turn drift. Measures stay-in-character format, not whether the voice is distinct.
| Model | Overall | Identity | Knowledge | Contradict | Jailbreak | Meta | Smalltalk | Drift |
|---|---|---|---|---|---|---|---|---|
| MiniNPC (this adapter) | 99% (90/91) | 100% | 100% | 92% | 100% | 100% | 100% | 100% |
| MiniCPM5-2B (no adapter) | 55% (50/91) |
Plug-in NPCs in games: one adapter, many characters via the system card. Not a general assistant.
Apache-2.0, same as the MiniCPM5-2B-SFT base.
| 77% |
| 62% |
| 23% |
| 31% |
| 92% |
| 62% |
| 38% |
| DeepSeek-Flash | 78% (71/91) | 85% | 85% | 62% | 85% | 100% | 77% | 54% |
| gpt-5.6-luna | 66% (60/91) | 100% | 100% | 46% | 15% | 100% | 69% | 31% |