Models

​

Available Models

​

Teacher Models

​

ATLAS-8B-Thinking

• Mathematical problem solving
• Logical reasoning
• Abstract thinking tasks
• Scientific analysis

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Arc-Intelligence/ATLAS-8B-Thinking",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(
    "Arc-Intelligence/ATLAS-8B-Thinking"
)

• Base model: Qwen2.5-7B-Instruct
• Training method: SFT → GRPO
• Specialization: Reasoning-heavy tasks

​

ATLAS-8B-Instruct

• Code generation
• Technical documentation
• System administration
• API integration

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"
)

• Base model: Qwen2.5-7B-Instruct
• Training method: SFT → GRPO
• Specialization: Instruction-following and coding

​

Model Selection Guide

​

Compatible Student Models

• Qwen/Qwen3-4B-Instruct (4B)
• meta-llama/Llama-3.2-8B-Instruct (8B)
• mistralai/Mixtral-8x7B-Instruct-v0.1 (47B)
• OpenAI GPT-4 (API)
• Anthropic Claude (API)

• Instruction-following capability
• Context window ≥4K tokens
• Support for system prompts (preferred)

​

Memory Requirements

​

Model Versioning

• Latest stable: No suffix (recommended for production)
• Experimental: -experimental suffix
• Specific versions: -v1.0, -v1.1, etc.

• Training data details
• Performance benchmarks
• Known limitations
• Update changelog

​

Custom Model Training

• GKD Training - Fast distillation (4-8 hours)
• GRPO Training - Full RL training (24-48 hours)
• Training Configuration - Parameter reference

​

License and Usage

• Verify outputs for critical applications
• Monitor for potential biases
• Respect base model licenses
• Cite ATLAS in publications

​

Next Steps