ArcOffical/PiCo-1B

PiCo 1B

A 1B-parameter dense language model optimized for reasoning and knowledge tasks. For clarity, our model uses the tokenizer from Qwen 2 1.5B but has been trained from scratch — it is not a fine-tuned version of Qwen 2 1.5B.

📌 Model Overview

PiCo 1B is a compact, high-performance language model with ~1.46 billion parameters. Despite its small size, it achieves competitive performance across reasoning, knowledge, and coding benchmarks, particularly excelling in science reasoning tasks.

📋 Model Details

📊 Benchmark Results

PiCo 1B is evaluated against 31 open-source models in the 1B–2B parameter range across 7 standard benchmarks.

MMLU (Massive Multitask Language Understanding)

Measures general knowledge across 57 subjects including STEM, humanities, and social sciences.

GSM8K (Grade School Math)

Measures mathematical reasoning with grade-school level word problems.

ARC-Challenge (AI2 Reasoning Challenge)

Measures science reasoning with grade-level science questions (harder subset).

ARC-Easy (AI2 Reasoning Challenge)

Measures basic science reasoning with grade-level science questions (easier subset).

HellaSwag (Commonsense Reasoning)

Measures commonsense natural language inference with everyday scenarios.

HumanEval (Code Generation)

Measures functional correctness of code generation across 164 programming problems.

TruthfulQA (Truthfulness)

Measures whether the model generates truthful answers rather than mimicking common misconceptions.

🏆 Performance Highlights

✅ Strengths

• —Science Reasoning: Best-in-class performance on ARC-Easy and ARC-Challenge
• —General Knowledge: Top 3 on MMLU, outperforming many larger 1.5B–2B models
• —Coding Ability: Strong HumanEval performance, competitive with models 2x its size
• —Truthfulness: Top 5 on TruthfulQA, demonstrating reliable factual output

📈 Areas for Improvement

• —Commonsense Reasoning: HellaSwag score lags behind modern 1.5B+ models
• —Mathematical Reasoning: GSM8K performance is solid but not top-tier
• —Scale: Further training on larger, more diverse datasets could boost all benchmarks

🚀 Usage

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "pico-1b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "Explain the theory of relativity in simple terms."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Model Formats

• —Safetensors (recommended): Secure and fast loading
• —PyTorch (FP16): Standard format
• —GGUF: For local inference with llama.cpp

🏋️ Training Details

⚠️ Limitations

• —Small Model Size: As a 1B-parameter model, it has inherent limitations compared to larger models (7B+) on complex reasoning tasks
• —Training Data: Primarily trained on English text; performance on non-English languages may be limited
• —Hallucinations: Like all LLMs, it may generate factually incorrect information
• —Context Window: Limited to 2048 tokens by default

📝 Citation

If you use PiCo 1B in your research or projects, please cite:

@misc{pico1b,
  title={PiCo 1B: A Compact Language Model Optimized for Reasoning},
  author={Arc Develop Team},
  year={2026},
  howpublished={\url{https://github.com/pico-llm/pico-1b}},
}

📄 License

This model is released under an open-source license. Please see the LICENSE file for details.

Last updated: June 2026