Instructions to use arcee-ai/Trinity-Large-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Trinity-Large-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/Trinity-Large-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Trinity-Large-Thinking", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Large-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use arcee-ai/Trinity-Large-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/Trinity-Large-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Large-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/Trinity-Large-Thinking

SGLang

How to use arcee-ai/Trinity-Large-Thinking 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-Large-Thinking" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Large-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-Large-Thinking" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Large-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/Trinity-Large-Thinking with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Trinity-Large-Thinking
```

Crystalcareai commited on Apr 1

Commit

80973c7

verified ·

1 Parent(s): 44bc97d

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +16 -5

chat_template.jinja CHANGED Viewed

@@ -98,13 +98,24 @@
     {%- if role == "assistant" %}
         {%- set content_str = '' if message.content is none else (message.content | string) %}
         {%- set trimmed_content = content_str | trim %}
         {%- set has_reasoning_content = message.reasoning_content is defined %}
         {%- set has_tool_calls = message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls is not string and message.tool_calls | length > 0 %}
         {{- '<|im_start|>assistant\n' }}
-        {%- if has_reasoning_content %}
-            {%- if message.reasoning_content %}
-                {{- '<think>' + (message.reasoning_content | string | trim) + '</think>' }}
             {%- else %}
                 {{- '<think></think>' }}
             {%- endif %}
@@ -121,7 +132,7 @@
         {%- if has_tool_calls %}
             {%- for tool_call in message.tool_calls %}
-                {%- set separator = '\n' if ((loop.first and (has_reasoning_content or trimmed_content)) or (not loop.first)) else '' -%}
                 {{- separator + render_tool_call(tool_call) }}
             {%- endfor %}
         {%- endif %}
@@ -145,4 +156,4 @@
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n<think>' }}
-{%- endif %}

     {%- if role == "assistant" %}
         {%- set content_str = '' if message.content is none else (message.content | string) %}
         {%- set trimmed_content = content_str | trim %}
         {%- set has_reasoning_content = message.reasoning_content is defined %}
+        {%- set has_reasoning = has_reasoning_content or (message.reasoning is defined) %}
+        {%- if has_reasoning_content %}
+            {%- set reasoning_value = message.reasoning_content %}
+        {%- elif message.reasoning is defined %}
+            {%- set reasoning_value = message.reasoning %}
+        {%- else %}
+            {%- set reasoning_value = none %}
+        {%- endif %}
         {%- set has_tool_calls = message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls is not string and message.tool_calls | length > 0 %}
         {{- '<|im_start|>assistant\n' }}
+        {%- if has_reasoning %}
+            {%- if reasoning_value %}
+                {{- '<think>' + (reasoning_value | string | trim) + '</think>' }}
             {%- else %}
                 {{- '<think></think>' }}
             {%- endif %}
         {%- if has_tool_calls %}
             {%- for tool_call in message.tool_calls %}
+                {%- set separator = '\n' if ((loop.first and (has_reasoning or trimmed_content)) or (not loop.first)) else '' -%}
                 {{- separator + render_tool_call(tool_call) }}
             {%- endfor %}
         {%- endif %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n<think>' }}
+{%- endif %}