README.md

metadata

base_model:
  - Qwen/Qwen3-4B
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

Apollo-1-4B

Apollo-1-4B is a 4 billion parameter instruction-tuned model developed by Noema Research.
It is based on Qwen3-4B and optimized for reasoning, instruction following, and lightweight deployment at scale.

This model represents the mid-size member of the Apollo series, balancing performance and efficiency for a broad range of use cases.

---

Model Overview

• Base model: Qwen3-4B
• Architecture: Decoder-only transformer
• Parameters: ~4B
• Context length: up to 32k tokens (inherits Qwen3 long-context support)
• Domain: General-purpose reasoning and instruction following
• Primary applications:
  • Conversational AI
  • Multi-step reasoning tasks
  • Education and tutoring systems
  • Knowledge assistants and prototyping agents
• License: anvdl-1.0

---

Key Features

• Instruction tuning for consistent conversational and task-oriented responses
• Improved reasoning depth compared to Apollo-1-2B, enabling stronger performance on complex queries
• Long-context handling, inherited from Qwen3 architecture
• Multilingual coverage, retaining broad knowledge across languages
• Balanced resource requirements, deployable on high-end consumer hardware and cloud GPUs

---

Usage

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

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "NoemaResearch/Apollo-1-4B"

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 helpful reasoning assistant."},
    {"role":"user", "content":"Summarize the main differences between reinforcement learning and supervised learning."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=768, temperature=0.6, top_p=0.9)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Recommended settings:

• temperature=0.4–0.8
• top_p=0.9–0.95
• Lower temperatures yield more factual and concise answers

---

Evaluation

Apollo-1-4B demonstrates stronger reasoning capabilities relative to Apollo-1-2B, with internal evaluations indicating:

• Higher accuracy on step-by-step reasoning tasks
• More robust instruction adherence
• Reduced hallucinations in factual settings
• Effective balance between performance and efficiency

A full benchmark report will be provided in a future update. For upstream performance details, see the Qwen3-4B model card.

---

Limitations

• Reasoning scale: While improved, Apollo-1-4B cannot match larger models (14B+) on complex or open-ended tasks
• Knowledge breadth: Some specialized or domain-specific knowledge remains limited
• Hallucinations: May generate plausible but incorrect information
• Prompt sensitivity: Outputs remain dependent on careful prompt formulation

---

Responsible Use

• Do not rely on Apollo-1-4B for critical decisions without human oversight
• Verify outputs before applying in factual, legal, or safety-critical contexts
• Avoid providing personal or sensitive data in prompts
• The model should not be used to generate unsafe, harmful, or disallowed content

---

Model Variants

• Full precision (safetensors) — research and high-fidelity inference
• bf16 / fp16 — efficient inference on modern accelerators
• Quantized versions (int8 / int4) — deployment in resource-constrained environments

---

Citation

If you use this model, please cite both Apollo-1-4B and the Qwen3 base model:

@misc{noema2025apollo4b,
  title={Apollo-1-4B},
  author={Noema Research},
  year={2025},
  howpublished={\url{https://huggingface.co/NoemaResearch/Apollo-1-4B}}
}

---

Acknowledgements

Apollo-1-4B builds upon the Qwen3 family of models. We thank the Qwen team for open-sourcing their models and enabling derivative research.

---