Instructions to use tripplet-research/suzhou3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tripplet-research/suzhou3.2 with Transformers:

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

pipe = pipeline("text-generation", model="tripplet-research/suzhou3.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tripplet-research/suzhou3.2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tripplet-research/suzhou3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tripplet-research/suzhou3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tripplet-research/suzhou3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tripplet-research/suzhou3.2

SGLang

How to use tripplet-research/suzhou3.2 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 "tripplet-research/suzhou3.2" \
    --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": "tripplet-research/suzhou3.2",
		"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 "tripplet-research/suzhou3.2" \
        --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": "tripplet-research/suzhou3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tripplet-research/suzhou3.2 with Docker Model Runner:
```
docker model run hf.co/tripplet-research/suzhou3.2
```

suzhou3.2 / README.md

alextripplet

Upload README.md with huggingface_hub

e0b9559 verified 12 days ago

preview code

raw

history blame contribute delete

1.4 kB

metadata

license: apache-2.0
language:
  - en
  - zh
  - ko
  - ja
  - fr
  - es
  - de
  - it
  - ru
  - ar
  - multilingual
pipeline_tag: text-generation
tags:
  - chat
  - suzhou
  - merged
  - reasoning
  - tool-use
  - agent
library_name: transformers
base_model:
  - tripplet-research/suzhou3.1
  - Qwen/Qwen2.5-3B-Instruct

Suzhou 3.2

A 12 billion parameter instruction-tuned language model by Triplet Research. Suzhou 3.2 is a weighted merge of Suzhou 3.1 and Qwen2.5-3B, designed to improve reasoning and math capabilities.

Merge Details

Method: Weighted blending (70% Suzhou 3.1 + 30% Qwen2.5-3B)
Model A: Suzhou 3.1 - strong agent/tool-use, reasoning
Model B: Qwen2.5-3B-Instruct - math reasoning, general knowledge
Target: 12B parameters

Key Features

12B parameters
262K context window
Strong reasoning and chain-of-thought capabilities
Tool calling and agent support
Multilingual support (29+ languages)
Mixed attention architecture (linear + full attention layers)

Architecture

Type: Causal Language Model
Architecture: Qwen3.5 Text
Layers: 32
Parameters: 12B

Safetensors

12B parameters

Quickstart

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Triplet-Research/suzhou-3.2")
tokenizer = AutoTokenizer.from_pretrained("Triplet-Research/suzhou-3.2")