Instructions to use junelegend/llama-3-docker-command-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use junelegend/llama-3-docker-command-lora with Transformers:

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

pipe = pipeline("text-generation", model="junelegend/llama-3-docker-command-lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("junelegend/llama-3-docker-command-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use junelegend/llama-3-docker-command-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "junelegend/llama-3-docker-command-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "junelegend/llama-3-docker-command-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/junelegend/llama-3-docker-command-lora

SGLang

How to use junelegend/llama-3-docker-command-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 "junelegend/llama-3-docker-command-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "junelegend/llama-3-docker-command-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "junelegend/llama-3-docker-command-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "junelegend/llama-3-docker-command-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use junelegend/llama-3-docker-command-lora 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 junelegend/llama-3-docker-command-lora 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 junelegend/llama-3-docker-command-lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for junelegend/llama-3-docker-command-lora to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="junelegend/llama-3-docker-command-lora",
    max_seq_length=2048,
)

Docker Model Runner
How to use junelegend/llama-3-docker-command-lora with Docker Model Runner:
```
docker model run hf.co/junelegend/llama-3-docker-command-lora
```

Uploaded model

Developed by: junelegend
License: apache-2.0
Finetuned from model : unsloth/llama-3-8b-bnb-4bit

Model Details

This model is finetuned on adeocybersecurity/DockerCommand dataset using the base unsloth/llama-3-8b-bnb-4bit model. These are only the lora adapaters of the model, the base model is automatically downloaded.

How to use

from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
  model_name = "llama-3-docker-command-lora",
  max_seq_length = max_seq_length,
  dtype = dtype,
  load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference

inputs = tokenizer(
[
    alpaca_prompt.format(
        "translate this sentence in docker command.", # instruction
        "Give me a list of all containers, indicating their status as well.", # input
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
tokenizer.batch_decode(outputs)

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.