GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sriq-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
sriq-ai
Model Tree
openbmb/MiniCPM5-2B
Input Modalities
Output Modalities
Supported Functionality
Reasoning is emitted inside <think> tags, then the answer:
text
<think>设 s=x+y，p=xy。…验：23*17=391。答案对。</think>x + y = 2 or 5. Working: …v1.5's training data ends every trace with a verification block — substituting the result back, re-deriving the invariant, walking the stated edge cases — before the answer is committed.
v1.5 is the dataset version that adds long system prompts simulating agentic coding harnesses. Earlier versions held Chinese reasoning under a short system prompt but drifted back to English behind a real agent harness — a multi-thousand-token English preamble of tool descriptions, skill listings and project context. 599 of the dataset's 1,424 rows carry such a preamble, so the behaviour is trained in the context where it otherwise collapses.
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM model_id = "sriq-ai/sriq-MiniCPM5-2B-v1.5"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto") messages = [{"role": "user", "content": "What is 17 * 23? Answer briefly."}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device) outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))enable_thinking=FalseThe chat template treats that flag as an instruction to skip reasoning, and prefills an empty block:
jinja
{%- if enable_thinking is false %} {{- '<think>\n\n</think>\n\n' }}The model then answers with no trace at all, silently — there is no error, and the behaviour this
model exists for is switched off. Leave the flag undefined, or set it to True.
| Base model | openbmb/MiniCPM5-2B |
| Parameters | 2,516,756,480 |
| Architecture | LlamaForCausalLM |
| Weights | bfloat16, merged (not an adapter) |
| Context length | 131,072 |
| Training data | sriq-ai/sriq-sft-v1.5 — 1,424 conversations, 30 languages, all difficulty: hard |
| Method | Supervised fine-tuning with Unsloth |
Quantizations: sriq-MiniCPM5-2B-v1.5-GGUF.
No benchmark results are published for this model. Nothing here describes measured gains in accuracy, verification rate, or answer quality — only what it was trained on and how it behaves. Evaluate on your own workload before relying on it.
Apache-2.0, inherited from the base model.
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM model_id = "sriq-ai/sriq-MiniCPM5-2B-v1.5"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto") messages = [{"role": "user", "content": "What is 17 * 23? Answer briefly."}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device) outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)){%- if enable_thinking is false %} {{- '<think>\n\n</think>\n\n' }}