Instructions to use syntropy-ai/Soren-1-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use syntropy-ai/Soren-1-Small with Transformers:

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

pipe = pipeline("text-generation", model="syntropy-ai/Soren-1-Small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("syntropy-ai/Soren-1-Small")
model = AutoModelForMultimodalLM.from_pretrained("syntropy-ai/Soren-1-Small")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use syntropy-ai/Soren-1-Small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "syntropy-ai/Soren-1-Small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "syntropy-ai/Soren-1-Small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/syntropy-ai/Soren-1-Small

SGLang

How to use syntropy-ai/Soren-1-Small 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 "syntropy-ai/Soren-1-Small" \
    --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": "syntropy-ai/Soren-1-Small",
		"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 "syntropy-ai/Soren-1-Small" \
        --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": "syntropy-ai/Soren-1-Small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use syntropy-ai/Soren-1-Small with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for syntropy-ai/Soren-1-Small to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for syntropy-ai/Soren-1-Small to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for syntropy-ai/Soren-1-Small to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="syntropy-ai/Soren-1-Small",
    max_seq_length=2048,
)

Docker Model Runner
How to use syntropy-ai/Soren-1-Small with Docker Model Runner:
```
docker model run hf.co/syntropy-ai/Soren-1-Small
```

Soren-1-Small / config.json

Andy-ML-And-AI

Initial commit — copy from Soren-2B-DPO2

5afc0aa verified 18 days ago

raw

history blame contribute delete

1.79 kB

	{
	"architectures": [
	"Qwen3_5ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 248046,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 6144,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 16,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 1048576,
	"mlp_only_layers": [],
	"model_name": "soren_dpo2_merged",
	"model_type": "qwen3_5_text",
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 8,
	"num_hidden_layers": 24,
	"num_key_value_heads": 2,
	"pad_token_id": 248044,
	"partial_rotary_factor": 0.25,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"factor": 4.0,
	"original_max_position_embeddings": 32768,
	"rope_type": "yarn",
	"type": "yarn"
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.9.0",
	"unsloth_version": "2026.5.8",
	"use_cache": false,
	"vocab_size": 248320
	}