Instructions to use arcee-ai/Trinity-Mini-Base-Pre-Anneal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Trinity-Mini-Base-Pre-Anneal with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="arcee-ai/Trinity-Mini-Base-Pre-Anneal", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Trinity-Mini-Base-Pre-Anneal", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Mini-Base-Pre-Anneal", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use arcee-ai/Trinity-Mini-Base-Pre-Anneal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/Trinity-Mini-Base-Pre-Anneal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Mini-Base-Pre-Anneal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arcee-ai/Trinity-Mini-Base-Pre-Anneal

SGLang

How to use arcee-ai/Trinity-Mini-Base-Pre-Anneal with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "arcee-ai/Trinity-Mini-Base-Pre-Anneal" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Mini-Base-Pre-Anneal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "arcee-ai/Trinity-Mini-Base-Pre-Anneal" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Mini-Base-Pre-Anneal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arcee-ai/Trinity-Mini-Base-Pre-Anneal with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Trinity-Mini-Base-Pre-Anneal
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Trinity Mini Base Pre Anneal

Trinity-Mini-Base-Pre-Anneal 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 is a pre-anneal checkpoint captured at Adam LR: 0.0002, Muon LR: 0.001 before starting learning rate decay on a high-quality data mix. While this checkpoint was not exposed to the anneal phase mix containing high proportions of math and code content, it has been trained on significant amounts of such data. This checkpoint is not suitable for chatting or general use without further finetuning and should be trained for your specific domain before use.

Trinity-Mini-Base-Pre-Anneal is trained on 8.8T 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

Model Details

Model Architecture: AfmoeForCausalLM
Parameters: 26B, 3B active
Experts: 128 total, 8 active, 1 shared
Context length: 4K
Learning rate during pretraining:
- adam_lr = 0.0002
- muon_lr = 0.001
Training Tokens: 8.8T
License: Apache 2.0

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?"
      }
    ]
  }'