Skip to content
Other

Qwen2.5-Coder-1.5B CLI

Experimental Linux Command Generator

1 min read

This model was trained using Supervised Fine-Tuning (SFT) with LoRA (a small adapter built on top of the base model) based on Qwen2.5-Coder-1.5B-Instruct. It turns natural language text prompts into Linux command-line instructions. The project was created as an experimental step toward a full-fledged system administration assistant. The model is delivered in GGUF format with Q4_K_M quantization, making it convenient for local execution.

Key features

  • Base: Qwen2.5-Coder-1.5B-Instruct
  • Training method: Supervised Fine-Tuning (SFT) with LoRA
  • Training data: 40,634 examples
  • Format: GGUF (Q4_K_M)

What you can do

  • Generate Linux shell commands from a text description of a task
  • Use it for assistance with basic system administration
  • Test the model capabilities locally for working with the console

Example

Prompt: "Find all files modified in the last 7 days and delete them"
Result: Generation of the corresponding file search and deletion command in the Linux terminal.

Read moreDetails
Accuracy (exact-match accuracy): baseline 11% → fine-tuned 18% (+7 percentage points)
Final training loss: 0.7867
Trainable parameters: 36.93M (2.34%)
Limitations: Experimental version, commands require verification before execution
Discuss Telegram 0

Will it run?

Runs in GGUF Q4_K_M

The most precise of the ready quantised files fits.

  • GGUF Q4_K_Mweights 0.9 GB · ready files1.5 GB

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: GGUF Q4_K_M — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Rachitvig/qwen25-coder-1.5b-cli-sft-experimental
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Rachitvig/qwen25-coder-1.5b-cli-sft-experimental --local-dir ~/models/qwen25-coder-1.5b-cli-sft-experimental
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of qwen25-coder-1.5b-cli-sft-experimental (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

Rachitvig/qwen25-coder-1.5b-cli-sft-experimental
Author
Rachitvig
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments