Instructions to use VictorMr/slm-terminal-specialist with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VictorMr/slm-terminal-specialist with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("VictorMr/slm-terminal-specialist")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use VictorMr/slm-terminal-specialist with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "VictorMr/slm-terminal-specialist"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "VictorMr/slm-terminal-specialist"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use VictorMr/slm-terminal-specialist with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "VictorMr/slm-terminal-specialist"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "VictorMr/slm-terminal-specialist"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "VictorMr/slm-terminal-specialist",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use VictorMr/slm-terminal-specialist with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "VictorMr/slm-terminal-specialist"

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 VictorMr/slm-terminal-specialist

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use VictorMr/slm-terminal-specialist with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "VictorMr/slm-terminal-specialist"

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 "VictorMr/slm-terminal-specialist" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

SLM Especialista em Terminal & Automacao CLI

Este modelo e um fine-tuning do Qwen/Qwen2.5-Coder-1.5B-Instruct otimizado para o ecossistema macOS (Apple Silicon) e terminal Unix/Zsh. Ele traduz pedidos em linguagem natural (portugues do Brasil) diretamente em comandos de terminal deterministas, precisos e sem explicacoes intermediarias.

Formato do Prompt (ChatML)

<|im_start|>system
Voce e um especialista em terminal Unix/macOS Zsh. Responda unica e exclusivamente com o comando pronto para execucao, sem explicacoes e sem formatacao markdown.<|im_end|>
<|im_start|>user
{sua intencao em portugues}<|im_end|>
<|im_start|>assistant

Caracteristicas

Modelo Base: Qwen/Qwen2.5-Coder-1.5B-Instruct
Treinamento: LoRA via MLX-LM no Apple Silicon
Dataset: 500 pares de instrucao validados cobrindo 60 utilitarios Unix (awk, sed, jq, ffmpeg, docker, git, etc.)
Repositorio de Codigo: https://github.com/contatovictorhugos-hash/slm-terminal-specialist

Downloads last month: 253

Safetensors

Model size

2B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for VictorMr/slm-terminal-specialist

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Finetuned

(204)

this model