Instructions to use SLT-AI/SLT-0.5b-GoToSpeak with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SLT-AI/SLT-0.5b-GoToSpeak with Transformers:

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

pipe = pipeline("text-generation", model="SLT-AI/SLT-0.5b-GoToSpeak")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SLT-AI/SLT-0.5b-GoToSpeak")
model = AutoModelForCausalLM.from_pretrained("SLT-AI/SLT-0.5b-GoToSpeak", device_map="auto")
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

llama.cpp

How to use SLT-AI/SLT-0.5b-GoToSpeak 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 SLT-AI/SLT-0.5b-GoToSpeak
# Run inference directly in the terminal:
llama cli -hf SLT-AI/SLT-0.5b-GoToSpeak

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SLT-AI/SLT-0.5b-GoToSpeak
# Run inference directly in the terminal:
llama cli -hf SLT-AI/SLT-0.5b-GoToSpeak

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 SLT-AI/SLT-0.5b-GoToSpeak
# Run inference directly in the terminal:
./llama-cli -hf SLT-AI/SLT-0.5b-GoToSpeak

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 SLT-AI/SLT-0.5b-GoToSpeak
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SLT-AI/SLT-0.5b-GoToSpeak

Use Docker

docker model run hf.co/SLT-AI/SLT-0.5b-GoToSpeak

LM Studio
Jan

vLLM

How to use SLT-AI/SLT-0.5b-GoToSpeak with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SLT-AI/SLT-0.5b-GoToSpeak"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SLT-AI/SLT-0.5b-GoToSpeak",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SLT-AI/SLT-0.5b-GoToSpeak

SGLang

How to use SLT-AI/SLT-0.5b-GoToSpeak 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 "SLT-AI/SLT-0.5b-GoToSpeak" \
    --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": "SLT-AI/SLT-0.5b-GoToSpeak",
		"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 "SLT-AI/SLT-0.5b-GoToSpeak" \
        --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": "SLT-AI/SLT-0.5b-GoToSpeak",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SLT-AI/SLT-0.5b-GoToSpeak with Ollama:
```
ollama run hf.co/SLT-AI/SLT-0.5b-GoToSpeak
```

Unsloth Studio

How to use SLT-AI/SLT-0.5b-GoToSpeak 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 SLT-AI/SLT-0.5b-GoToSpeak 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 SLT-AI/SLT-0.5b-GoToSpeak to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SLT-AI/SLT-0.5b-GoToSpeak to start chatting

How to use SLT-AI/SLT-0.5b-GoToSpeak with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SLT-AI/SLT-0.5b-GoToSpeak

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": "SLT-AI/SLT-0.5b-GoToSpeak"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SLT-AI/SLT-0.5b-GoToSpeak with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SLT-AI/SLT-0.5b-GoToSpeak

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 SLT-AI/SLT-0.5b-GoToSpeak

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use SLT-AI/SLT-0.5b-GoToSpeak with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SLT-AI/SLT-0.5b-GoToSpeak

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 "SLT-AI/SLT-0.5b-GoToSpeak" \
  --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 SLT-AI/SLT-0.5b-GoToSpeak with Docker Model Runner:
```
docker model run hf.co/SLT-AI/SLT-0.5b-GoToSpeak
```

Lemonade

How to use SLT-AI/SLT-0.5b-GoToSpeak with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SLT-AI/SLT-0.5b-GoToSpeak

Run and chat with the model

lemonade run user.SLT-0.5b-GoToSpeak-{{QUANT_TAG}}

List all available models

lemonade list

SLT-0.5b-GoToSpeak

A small 0.5B parameter conversational model based on Qwen2.5-0.5B.

Training Dataset

The model was fine-tuned on 7500 examples.

The dataset includes:

Conversational dialogues in Russian and English
Up-to-date general knowledge (as of 2025-2026)
Simple Python coding tasks
Basic mathematics with step-by-step explanations

Training method: Supervised Fine-Tuning (SFT).

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "SLT-AI/SLT-0.5b-GoToSpeak"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, 
    torch_dtype=torch.bfloat16, 
    device_map="auto"
)

messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs, 
    max_new_tokens=512, 
    temperature=0.7, 
    top_p=0.9
)

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

Downloads last month: 209

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for SLT-AI/SLT-0.5b-GoToSpeak

Base model

Qwen/Qwen2.5-0.5B

Quantized

(111)

this model