Instructions to use PLAZMAstudios/Codestal-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PLAZMAstudios/Codestal-Mini with Transformers:

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

pipe = pipeline("text-generation", model="PLAZMAstudios/Codestal-Mini")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PLAZMAstudios/Codestal-Mini")
model = AutoModelForCausalLM.from_pretrained("PLAZMAstudios/Codestal-Mini")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PLAZMAstudios/Codestal-Mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PLAZMAstudios/Codestal-Mini

SGLang

How to use PLAZMAstudios/Codestal-Mini 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 "PLAZMAstudios/Codestal-Mini" \
    --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": "PLAZMAstudios/Codestal-Mini",
		"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 "PLAZMAstudios/Codestal-Mini" \
        --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": "PLAZMAstudios/Codestal-Mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PLAZMAstudios/Codestal-Mini with Docker Model Runner:
```
docker model run hf.co/PLAZMAstudios/Codestal-Mini
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.


Codestal-Mini 2,5M examples.
Everyone can use.
100% Free!

Why Codestal?

-Codestal Models can be listed as "Mini", "Legacy", "V-version.number-" and "Pro"

-Codestal Models are 100% free.

DON'T FORGET!

-Add the dev's name(s) when you use a Codestal Model fine-tuned by someone else.

-Codestal-V1-Mini (You are here) (2,5M examples)

-Codestal-V1 (10M-Examples) (Unverified)

-Codestal-V1-Pro (50M Examples) (Unverified)

Downloads last month: -

Safetensors

Model size

13.4M params

Tensor type

F32