Trinity-Large-Thinking

// API response structure
{
  "message": {
    "role": "assistant",
    "reasoning": "The user wants flight information. I need to determine the date for next Tuesday, search for flights SFO → JFK, and filter by price < $300.",
    "content": "\n",
    "tool_calls": [{
      "function": {
        "name": "search_flights",
        "arguments": "{\"origin\": \"SFO\", \"destination\": \"JFK\", \"date\": \"2026-04-07\", \"max_price\": 300}"
      }
    }]
  }
}

vllm serve arcee-ai/Trinity-Large-Thinking \
  --dtype bfloat16 \
  --reasoning-parser deepseek_r1 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder

from openai import OpenAI

client = OpenAI(api_key="EMPTY", base_url="http://localhost:8000/v1")

response = client.chat.completions.create(
    model="arcee-ai/Trinity-Large-Thinking",
    messages=[
        {"role": "user", "content": "What's the weather like in Paris?"}
    ],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {"location": {"type": "string"}},
                "required": ["location"]
            }
        }
    }],
)

# Access reasoning (thinking) content
reasoning = response.choices[0].message.reasoning_content

# Access final response or tool calls
content = response.choices[0].message.content
tool_calls = response.choices[0].message.tool_calls

import json
from openai import OpenAI

client = OpenAI(api_key="EMPTY", base_url="http://localhost:8000/v1")
MODEL = "arcee-ai/Trinity-Large-Thinking"

tools = [
    {"type": "function", "function": {
        "name": "get_customer_by_email",
        "description": "Look up a customer by email.",
        "parameters": {"type": "object", "properties": {"email": {"type": "string"}}, "required": ["email"]}
    }},
    {"type": "function", "function": {
        "name": "cancel_subscription",
        "description": "Cancel a subscription. Requires customer_id.",
        "parameters": {"type": "object", "properties": {"customer_id": {"type": "string"}, "reason": {"type": "string"}}, "required": ["customer_id"]}
    }}
]

def execute_tool(name, arguments):
    """Simulate tool execution — replace with real implementations."""
    args = json.loads(arguments)
    if name == "get_customer_by_email":
        return json.dumps({"customer_id": "C2001", "name": "Jane Doe", "plan": "Premium", "status": "active"})
    elif name == "cancel_subscription":
        return json.dumps({"success": True, "message": f"Subscription cancelled for {args['customer_id']}"})

messages = [
    {"role": "system", "content": "You are a helpful customer service agent."},
    {"role": "user", "content": "I want to cancel my subscription. My email is jane@example.com"}
]

# Agent loop
while True:
    response = client.chat.completions.create(
        model=MODEL, messages=messages, tools=tools,
        tool_choice="auto", temperature=0, max_tokens=1000
    )
    msg = response.choices[0].message

    # Build assistant message — PRESERVE the reasoning field
    assistant_msg = {"role": "assistant", "content": msg.content}
    if msg.reasoning_content:
        assistant_msg["reasoning"] = msg.reasoning_content  # ← critical for multi-turn
    if msg.tool_calls:
        assistant_msg["tool_calls"] = [
            {"id": tc.id, "type": "function", "function": {"name": tc.function.name, "arguments": tc.function.arguments}}
            for tc in msg.tool_calls
        ]
    messages.append(assistant_msg)

    # If no tool calls, model gave its final response — done
    if not msg.tool_calls:
        print(f"Final response: {msg.content}")
        break

    # Execute tool calls and append results
    for tc in msg.tool_calls:
        result = execute_tool(tc.function.name, tc.function.arguments)
        print(f"  Tool: {tc.function.name}({tc.function.arguments}) → {result}")
        messages.append({"role": "tool", "tool_call_id": tc.id, "content": result})

  Tool: get_customer_by_email({"email": "jane@example.com"}) → {"customer_id": "C2001", ...}
  Tool: cancel_subscription({"customer_id": "C2001", ...}) → {"success": true, ...}
  Final response: Your subscription has been cancelled successfully.

assistant_msg["reasoning"] = msg.reasoning_content  # ← pass reasoning back as "reasoning"

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "arcee-ai/Trinity-Large-Thinking"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role": "user", "content": "Who are you?"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=4096,
    do_sample=True,
    temperature=0.6,
    top_k=50,
    top_p=0.95
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

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-large-thinking",
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
  }'

{"debug": {"echo_upstream_body": true}}

@misc{singh2026arceetrinity,
  title        = {Arcee Trinity Large Technical Report},
  author       = {Varun Singh and Lucas Krauss and Sami Jaghouar and Matej Sirovatka and Charles Goddard and Fares Obied and Jack Min Ong and Jannik Straube and Fern and Aria Harley and Conner Stewart and Colin Kealty and Maziyar Panahi and Simon Kirsten and Anushka Deshpande and Anneketh Vij and Arthur Bresnu and Pranav Veldurthi and Raghav Ravishankar and Hardik Bishnoi and DatologyAI Team and Arcee AI Team and Prime Intellect Team and Mark McQuade and Johannes Hagemann and Lucas Atkins},
  year         = {2026},
  eprint       = {2602.17004},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  doi          = {10.48550/arXiv.2602.17004},
  url          = {https://arxiv.org/abs/2602.17004}
}