Trinity Mini Base
Trinity Mini is an Arcee AI 26B MoE model with 3B active parameters. It is the medium-sized model in our new Trinity family, a series of open-weight models for enterprise and tinkerers alike.
This base model pre fine tuning, and so is not suitable for chatting, and should be trained for your specific domain before use.
Trinity Mini is trained on 10T tokens gathered and curated through a key partnership with Datology, building upon the excellent dataset we used on AFM-4.5B with additional math and code.
Training was performed on a cluster of 512 H200 GPUs powered by Prime Intellect using HSDP parallelism.
More details, including key architecture decisions, can be found on our blog here
Try it out the reasoning model now at chat.arcee.ai or download here: arcee-ai/Trinity-Mini
Model Details
- Model Architecture: AfmoeForCausalLM
- Parameters: 26B, 3B active
- Experts: 128 total, 8 active, 1 shared
- Context length: 128k
- Training Tokens: 10T
- License: OpenMDW-1.1
Benchmarks
General Benchmarks
| Benchmark | Score |
|---|---|
| ARC-Challenge | 90.0% |
| CommonsenseQA | 79.6% |
| OpenBookQA | 89.0% |
| Winogrande | 75.9% |
| MMLU (5-shot) | 74.7% |
| AGI Eval English | 61.8% |
| BBH CoT (3-shot) | 54.2% |
| MMLU Pro | 45.6% |
Math & Code Benchmarks
| Benchmark | Score |
|---|---|
| GSM8K | 56.6% |
| Minerva MATH 500 | 51.8% |
| HumanEval+ | 57.3% |
| MBPP+ | 55.3% |
Try out our reasoning tune
Trinity Mini is available today on openrouter:
https://openrouter.ai/arcee-ai/trinity-mini
curl -X POST "https://openrouter.ai/v1/chat/completions" \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "arcee-ai/trinity-mini",
"messages": [
{
"role": "user",
"content": "What are some fun things to do in New York?"
}
]
}'
License
Trinity-Mini-Base is released under the OpenMDW-1.1 license.