Hugging Face's logo

NoemaResearch
/
Apollo-1-2B

Text Generation
Transformers
Safetensors
qwen3
text-generation-inference
unsloth
conversational
Model card Files
xet
Community
Apollo-1-2B / README.md
Spestly's picture
Spestly
Update README.md
7354f15 verified
preview code
|
raw
history blame contribute delete
5.88 kB
metadata
base_model:
  - Qwen/Qwen3-1.7B
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen3
license: other
license_name: anvdl-1.0
license_link: https://huggingface.co/apexion-ai/Nous-V1-8B/blob/main/LICENSE.md
language:
  - en
  - fr
  - pt
  - de
  - ro
  - sv
  - da
  - bg
  - ru
  - cs
  - el
  - uk
  - es
  - nl
  - sk
  - hr
  - pl
  - lt
  - nb
  - nn
  - fa
  - sl
  - gu
  - lv
  - it
  - oc
  - ne
  - mr
  - be
  - sr
  - lb
  - vec
  - as
  - cy
  - szl
  - ast
  - hne
  - awa
  - mai
  - bho
  - sd
  - ga
  - fo
  - hi
  - pa
  - bn
  - or
  - tg
  - yi
  - lmo
  - lij
  - scn
  - fur
  - sc
  - gl
  - ca
  - is
  - sq
  - li
  - prs
  - af
  - mk
  - si
  - ur
  - mag
  - bs
  - hy
  - zh
  - yue
  - my
  - ar
  - he
  - mt
  - id
  - ms
  - tl
  - ceb
  - jv
  - su
  - min
  - ban
  - pag
  - ilo
  - war
  - ta
  - te
  - kn
  - ml
  - tr
  - az
  - uz
  - kk
  - ba
  - tt
  - th
  - lo
  - fi
  - et
  - hu
  - vi
  - km
  - ja
  - ko
  - ka
  - eu
  - ht
  - pap
  - kea
  - tpi
  - sw

banner

Apollo-1-2B

Model Base License

Apollo-1-2B is a 2 billion parameter instruction-tuned model developed by Noema Research.
It is based on Qwen3-1.7B and optimized for general reasoning, language understanding, and lightweight deployment.

This model is the first release in the Apollo series, intended as a foundation for scalable experimentation and real-world applications in constrained environments.

Model Overview

  • Base model: Qwen3-1.7B
  • Architecture: Decoder-only transformer
  • Parameters: ~2B
  • Context length: up to 32k tokens (inherits Qwen3 long-context support)
  • Domain: General-purpose reasoning and instruction following
  • Primary applications:
    • Conversational AI
    • Lightweight reasoning tasks
    • Education and tutoring
    • Prototype agents and assistants
  • License: anvdl-1.0

Key Features

  • Instruction tuned: More reliable responses in conversational and task-oriented settings
  • Lightweight deployment: Optimized for environments with limited compute or memory resources
  • Extended context: Inherits long-context capability from Qwen3 base
  • Balanced outputs: Improved refusal behaviors and reduced hallucinations compared to the base model
  • Multilingual ability: Retains multilingual knowledge from Qwen3 family

Usage

The model is available in Hugging Face Transformers format. Example:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "NoemaResearch/Apollo-1-2B"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role":"system", "content":"You are Apollo, a reasoning assistant."},
    {"role":"user", "content":"Explain the difference between supervised and unsupervised learning."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Recommended settings:

  • temperature=0.5–0.9
  • top_p=0.85–0.95
  • For structured outputs (e.g. JSON), use lower temperatures for stability

Evaluation

Apollo-1-2B has been evaluated internally on a range of reasoning and language tasks. Key findings:

  • Improved instruction following relative to Qwen3-1.7B
  • More concise and accurate responses in structured tasks
  • Maintains multilingual performance from the base model
  • Effective for lightweight assistant applications

Future work will include publishing comprehensive benchmark comparisons against other models in the 1–3B parameter range.

Limitations

  • Reasoning depth: As a 2B parameter model, Apollo cannot match larger-scale LLMs on complex reasoning tasks
  • Knowledge coverage: May lack depth in specialized or low-resource domains
  • Hallucinations: Although reduced, the model may still generate incorrect or fabricated information
  • Sensitivity to prompts: Outputs vary with prompt phrasing; careful prompt design recommended

Responsible Use

  • Do not rely on Apollo for critical decision-making without human oversight
  • Generated outputs may contain inaccuracies; verification is required for factual or sensitive use cases
  • Avoid providing personal, private, or sensitive information in prompts
  • This model should not be used to generate disallowed, unsafe, or harmful content

Model Variants

  • Full precision (safetensors) — research and full-fidelity inference
  • bf16 / fp16 — optimized for inference on GPUs/TPUs
  • Quantized versions (int8 / int4) — for deployment in constrained hardware environments

Citation

If you use this model, please cite both Apollo-1-2B and the Qwen3 base model:

@misc{noema2025apollo,
  title={Apollo-1-2B},
  author={Noema Research},
  year={2025},
  howpublished={\url{https://huggingface.co/NoemaResearch/Apollo-1-2B}}
}

Acknowledgements

Apollo-1-2B builds upon the Qwen3 series of models. We thank the Qwen team for making their work openly available under permissive terms, which enabled this derivative research.