Model Card for MiniCPM-1B Calibrated (Anti-Hallucination & Anti-Sycophancy)

A calibrated 1.08B parameter language model aligned with Identity Preference Optimization (IPO) to eliminate hallucination, resist sycophancy, and prevent over-refusal.

Model Details

Model Description

MiniCPM-1B Calibrated is an instruction-tuned and preference-aligned decoder-only causal language model (~1.08B parameters). It is specifically calibrated to address the two primary failure modes of small parameter models:

1. Sycophancy & Hallucinatory Deference: Agreeing with user fallacies or confabulating answers when context is unanswerable.
2. Over-Refusal Collapse: Failing to answer valid, answerable questions due to unbounded standard preference loss.

By applying Identity Preference Optimization (IPO) on a debiased 4-way multi-task dataset, the model establishes a mathematically bounded margin between truthful and sycophantic/hallucinatory outputs.

• Developed by: ewinregirgojr
• Model type: Causal Language Model (Transformer Decoder)
• Language(s) (NLP): English (en)
• License: Apache-2.0
• Finetuned from model: openbmb/MiniCPM-1B-sft-bf16
• Context Length: 2,048 tokens

Uses

Direct Use

• Context-grounded Question Answering with factual abstention when context lacks evidence.
• Misconception correction and objective dialogue without deferential sycophancy.
• Edge, on-device, and low-latency inference environments.

Out-of-Scope Use

• Generation of deceptive, malicious, or ungrounded factual assertions.
• High-stakes autonomous medical, legal, or financial decisions without human verification.

Bias, Risks, and Limitations

• Parameter Constraints (1.08B): Complex multi-step symbolic reasoning is bounded by model capacity relative to 7B+ scale models.
• Domain Specialization: Highly technical domains require pairing with retrieval-augmented generation (RAG).

Training Details

Training Data

The model was aligned on a debiased, deduplicated 4-way balanced mixture:

1. 35% UltraFeedback General Anchor (HuggingFaceH4/ultrafeedback_binarized): Maintains general knowledge, instruction following, and reasoning.
2. 25% SQuAD v2 Answerable Pairs (rajpurkar/squad_v2): Trains factual recall and eliminates false-positive over-refusals.
3. 20% SQuAD v2 Unanswerable Traps (rajpurkar/squad_v2): Enforces honest abstention when provided context lacks sufficient evidence.
4. 20% Sycophancy Reversal Pairs (auditing-agents/rm_sycophancy_dpo): Eliminates deferential confirmation of user misconceptions and leading fallacies.

Training Procedure

Training Hyperparameters

• Objective: Identity Preference Optimization (IPO) with quadratic penalty
• Regularization (beta / tau): beta = 0.1 (tau = 10.0)
• Learning Rate: 5e-6 with Cosine Annealing decay
• Warmup Steps: 15 steps
• Batch Size: 3 per device, Gradient Accumulation: 4 (Effective batch size = 12)
• Optimizer: AdamW ((beta1, beta2) = (0.9, 0.999), epsilon = 1e-8)
• Adapter Configuration (PEFT LoRA): r=16, alpha=32, dropout=0.05 across all projection layers (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)
• Precision: Bfloat16 with Scaled Dot-Product Attention (SDPA)
• Epochs: 2.0 (272 total optimization steps)

Evaluation

Testing Data, Factors & Metrics

Evaluated on an out-of-distribution held-out validation split (183 pairs) across answerable QA, unanswerable traps, sycophancy reversals, and general reasoning anchors.

Results

Environmental Impact

• Hardware Type: 1 x NVIDIA Tesla T4 GPU (16 GB VRAM)
• Hours used: ~2.5 GPU hours
• Cloud Provider: Google Cloud Platform (via Colab CLI persistent engine)
• Carbon Emitted: ~0.28 kg CO2eq (estimated via ML Impact calculator)

Technical Specifications

• Architecture: MiniCPM Causal LM with ChatML formatting
• Vocabulary Size: 73,440 tokens
• Special Tokens: <|im_start|>, <|im_end|>

How to Get Started with the Model

Python (transformers)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ewinregirgojr/minicpm5-1b-calibrated-anti-hallucination-sycophancy"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16,
    device_map="auto",
    trust_remote_code=True
)

prompt = """<|im_start|>system
You are a helpful, factual, and unbiased assistant.<|im_end|>
<|im_start|>user
Isn't it proven that 5G towers spread airborne viruses?<|im_end|>
<|im_start|>assistant
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=150,
    temperature=0.2,
    top_p=0.9,
    eos_token_id=tokenizer.eos_token_id
)

response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)

High-Level Pipeline

from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="ewinregirgojr/minicpm5-1b-calibrated-anti-hallucination-sycophancy",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role": "system", "content": "You are a helpful and precise assistant."},
    {"role": "user", "content": "Context: The speed of light in vacuum is exactly 299,792,458 m/s.\n\nQuestion: What is the exact speed of light?"}
]

output = pipe(messages, max_new_tokens=100, temperature=0.1)
print(output[0]["generated_text"][-1]["content"])

Quantized Formats (GGUF)

For local edge deployments (llama.cpp, Ollama, LM Studio), quantized GGUF weights are available: 👉 ewinregirgojr/minicpm5-1b-calibrated-anti-hallucination-sycophancy-GGUF

Citation

@misc{minicpm1b_calibrated_2026,
  author = {ewinregirgojr},
  title = {MiniCPM-1B Calibrated: Anti-Hallucination & Anti-Sycophancy via Identity Preference Optimization},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ewinregirgojr/minicpm5-1b-calibrated-anti-hallucination-sycophancy}}
}

Model Card Authors

ewinregirgojr

Model Card Contact

For questions or issues, please open a discussion on the Hugging Face Community tab.