Instructions to use strykes/SteraVibeThinker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use strykes/SteraVibeThinker with Transformers:

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

pipe = pipeline("text-generation", model="strykes/SteraVibeThinker")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("strykes/SteraVibeThinker", dtype="auto")

llama-cpp-python

How to use strykes/SteraVibeThinker with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="strykes/SteraVibeThinker",
	filename="SteraVibeThinker-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use strykes/SteraVibeThinker with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf strykes/SteraVibeThinker:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf strykes/SteraVibeThinker:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf strykes/SteraVibeThinker:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf strykes/SteraVibeThinker:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf strykes/SteraVibeThinker:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf strykes/SteraVibeThinker:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf strykes/SteraVibeThinker:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf strykes/SteraVibeThinker:Q4_K_M

Use Docker

docker model run hf.co/strykes/SteraVibeThinker:Q4_K_M

LM Studio
Jan

vLLM

How to use strykes/SteraVibeThinker with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/strykes/SteraVibeThinker:Q4_K_M

SGLang

How to use strykes/SteraVibeThinker 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 "strykes/SteraVibeThinker" \
    --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": "strykes/SteraVibeThinker",
		"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 "strykes/SteraVibeThinker" \
        --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": "strykes/SteraVibeThinker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use strykes/SteraVibeThinker with Ollama:
```
ollama run hf.co/strykes/SteraVibeThinker:Q4_K_M
```

Unsloth Studio

How to use strykes/SteraVibeThinker 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 strykes/SteraVibeThinker 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 strykes/SteraVibeThinker to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for strykes/SteraVibeThinker to start chatting

How to use strykes/SteraVibeThinker with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf strykes/SteraVibeThinker:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "strykes/SteraVibeThinker:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use strykes/SteraVibeThinker with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf strykes/SteraVibeThinker:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default strykes/SteraVibeThinker:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use strykes/SteraVibeThinker with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf strykes/SteraVibeThinker:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "strykes/SteraVibeThinker:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use strykes/SteraVibeThinker with Docker Model Runner:
```
docker model run hf.co/strykes/SteraVibeThinker:Q4_K_M
```

Lemonade

How to use strykes/SteraVibeThinker with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull strykes/SteraVibeThinker:Q4_K_M

Run and chat with the model

lemonade run user.SteraVibeThinker-Q4_K_M

List all available models

lemonade list

SteraVibeThinker

A full fine-tune of WeiboAI/VibeThinker-3B (a 3B reasoning model built on the Qwen2.5-3B / Qwen2.5-Coder-3B architecture) on the ~30k-example Tiny-Giant agentic tool-use dataset.

The goal: keep VibeThinker's strong verifiable-reasoning core while teaching it the deterministic, Hermes/ChatML-style <tool_call> agent format used by the Tiny-Giant harness.

Files

File	Description
`SteraVibeThinker-Q4_K_M.gguf`	Q4_K_M quantization (~1.8 GB) — for `llama.cpp` / Ollama / LM Studio
`SteraVibeThinker-f16.gguf`	f16 GGUF (~5.8 GB) — re-quantize to any level without retraining
`raw_weights/`	Full bf16 safetensors HF checkpoint
`val_meta.jsonl`	Held-out validation set shipped with the model

Training

Base: WeiboAI/VibeThinker-3B (MIT, Qwen2.5-3B architecture, ChatML-native)
Method: full fine-tune (not LoRA), bf16 + gradient checkpointing
Data: ~30k Tiny-Giant agentic tool-use conversations
Epochs: 2 · LR: 7e-6 (cosine, 3% warmup) · Seq len: 4096
Loss: full-sequence (tool results modeled as in-distribution context)

Prompt format

This model was trained with an explicit ChatML / Hermes renderer, not tokenizer.apply_chat_template. Pin the ChatML template explicitly when serving — do not rely on auto-detection. Tool calls use:

<tool_call>
{"name": "<function-name>", "arguments": {...}}
</tool_call>

Inference (llama.cpp)

llama-cli -m SteraVibeThinker-Q4_K_M.gguf --chat-template chatml

License

MIT, inherited from the VibeThinker-3B base model.

Downloads last month: 190

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

16-bit

Model tree for strykes/SteraVibeThinker

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

WeiboAI/VibeThinker-3B

Quantized

(53)

this model