Arc-Intelligence

ATLAS-Teach-8B-Instruct

README

License: apache-2.0

Model's Role in the ATLAS Framework

The ATLAS training pipeline is a two-stage process:

Phase 1: Supervised Fine-Tuning (SFT) → This is the phase that produces ATLAS-8B-Instruct. It learns the core knowledge and teaching formats from a static dataset.
Phase 2: Reinforcement Learning (RL) → This phase takes ATLAS-8B-Instruct as its starting point and trains it to become an adaptive teacher, resulting in the final ATLAS-8B-Thinking model.

This checkpoint is released for researchers who wish to replicate our work, build upon the SFT foundation, or experiment with the second-stage RL training.

How to Use

ATLAS-8B-Instruct is not a general-purpose chat model. It is designed to generate teaching content based on the structured format used in our dataset.

Basic Generation Example

python

from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained(    "Arc-Intelligence/ATLAS-8B-Instruct",    torch_dtype="auto",    device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Arc-Intelligence/ATLAS-8B-Instruct") # Example prompt following the SFT formatprompt = """Question: A farmer has 52 trees planted in a row over a length of 1850 meters. What is the distance between each tree? Provide a step-by-step explanation to solve this problem.""" inputs = tokenizer(prompt, return_tensors="pt").to("cuda")outputs = model.generate(    **inputs,    max_new_tokens=512,    temperature=0.7,    do_sample=True)response = tokenizer.decode(outputs[0], skip_special_tokens=True)print(response)

Continuing to RL Training

This model is the direct input for the second phase of the ATLAS training pipeline. To use this model as the base for RL training, follow the instructions in the main repository.

bash

# In the ATLAS repository, the RL script is configured# to load an SFT checkpoint like this one. # Run Phase 2: Reinforcement Learning (RL)scripts/launch_with_server.sh 1 3 configs/run/teacher_rcl.yaml

Training Details

Base Model: Qwen/Qwen3-8B
Training Stage: Supervised Fine-Tuning (SFT) only
Dataset: Arc-Intelligence/Arc-ATLAS-Teach-v0
Context Length: 8192 tokens
Hardware: 4x H100 GPUs
Precision: BF16
Framework: DeepSpeed ZeRO-3

Limitations

Pre-RL Checkpoint: This model has not undergone the reinforcement learning optimization that teaches adaptive teaching. The full performance gains reported in our paper are only realized after the RL phase.
Domain Scope: Primarily trained on the mathematical and reasoning problems present in the Arc-ATLAS-Teach-v0 dataset.
Not for Chat: The model is not intended for conversational use and performs best with prompts that match the SFT data format.

Citation

If you use the ATLAS framework or our models in your research, please cite our work:

bibtex

@misc{barnes2025atlas,      title={{ATLAS: Adaptive Teaching and Learning Alignment System for Reinforcement Learning}},       author={Jarrod Barnes and Aman Jaglan},      year={2025},      publisher={Arc Intelligence},      note={Technical Report},      url={[https://github.com/Arc-Computer/ATLAS](https://github.com/Arc-Computer/ATLAS)}}

Project Resources

GitHub Repository: https://github.com/Arc-Computer/ATLAS
Final RL Model: ATLAS-8B-Thinking
Training Dataset: Arc-ATLAS-Teach-v0

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

Arc-Intelligence

Model Tree

Base

Qwen/Qwen3-8B

Fine-tuned

this model

Input Modalities

Text

Output Modalities