Cogito v2 preview - 109B MoE

This is a hybrid reasoning model. To enable thinking mode, pass the following parameter with your request to the model:

    
"chat_template_kwargs": {"enable_thinking": true}
    

Here's an example cURL request with thinking enabled:

    
curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
    -d '{
    "model": "deepcogito/cogito-v2-preview-llama-109B-MoE",
    "temperature": 0.6,
    "chat_template_kwargs": {"enable_thinking": true},
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
}'
    

Here's an example Python request with thinking enabled:

    
from together import Together

client = Together()

chat_template_kwargs = {"enable_thinking": True}

response = client.chat.completions.create(
  model="deepcogito/cogito-v2-preview-llama-109B-MoE"",
  extra_body={"chat_template_kwargs": chat_template_kwargs},
  messages=[
    {
      "role": "user",
      "content": "What are some fun things to do in New York?"
    }
  ]
)
print(response.choices[0].message.content)
    

‍
Architecture Overview:
• 109B MoE mixture-of-experts architecture with intelligent routing
• Strong reasoning capabilities in the Cogito model family
• Advanced policy improvement for both reasoning and non-reasoning modes

Training Methodology:
• Dual-mode training improving both standard and reasoning performance
• Signal-based training for thinking process optimization
• Advanced distillation techniques preventing reasoning meandering

Performance Characteristics:
• Excellent reasoning performance in 109B MoE parameter class
• Efficient inference with optimized reasoning chains
• Strong performance across diverse reasoning benchmarks

Complex Reasoning Tasks:
• Multi-step mathematical proofs and scientific analysis
• Logical reasoning requiring expert knowledge activation
• Research synthesis across multiple domains

Multimodal Analysis:
• Image comparison and visual reasoning tasks
• Document analysis with text and visual components
• Educational content requiring cross-modal understanding

Efficiency-Critical Applications:
• Real-time reasoning with computational constraints
• Batch processing of diverse reasoning tasks
• Scalable AI applications requiring expert-level performance

‍