Instructions to use mjpsm/qwen-bash-experiment-model-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mjpsm/qwen-bash-experiment-model-lora with Transformers:

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

pipe = pipeline("text-generation", model="mjpsm/qwen-bash-experiment-model-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mjpsm/qwen-bash-experiment-model-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mjpsm/qwen-bash-experiment-model-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mjpsm/qwen-bash-experiment-model-lora

SGLang

How to use mjpsm/qwen-bash-experiment-model-lora 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 "mjpsm/qwen-bash-experiment-model-lora" \
    --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": "mjpsm/qwen-bash-experiment-model-lora",
		"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 "mjpsm/qwen-bash-experiment-model-lora" \
        --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": "mjpsm/qwen-bash-experiment-model-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mjpsm/qwen-bash-experiment-model-lora with Docker Model Runner:
```
docker model run hf.co/mjpsm/qwen-bash-experiment-model-lora
```

Qwen3-4B Bash Tool Calling LoRA

This model is a LoRA fine-tune of Qwen3-4B trained to predict bash tool calls from natural language instructions.

Purpose

The goal of this project was to learn and understand how modern AI tool calling works under the hood by training a language model to map natural language requests into structured tool invocations.

The model predicts bash commands rather than executing them directly.

Example:

Input:

What is my system information?

Output:

<tool_call>
{"name":"bash","arguments":{"command":"uname -a"}}
</tool_call>

Training Data

The dataset contains synthetic bash tool-calling examples generated using Llama 3.2.

Supported command categories:

Navigation
- pwd
- ls
- ls -la
System Information
- whoami
- hostname
- uname -a
File Creation
- mkdir
- touch

Examples are formatted as tool-calling conversations.

Base Model

Qwen/Qwen3-4B

Fine-Tuning Method

LoRA (PEFT)

Configuration:

Rank (r): 16
Alpha: 32
Dropout: 0.05

Evaluation

Command prediction accuracy:

100%

Intended Use

This model is intended for:

Learning tool calling
Educational projects
Agent experimentation
Bash command prediction

This model is not intended for production deployment or unrestricted command execution.

Author

Mazamesso Meba

Downloads last month: -; Downloads are not tracked for this model. How to track