Instructions to use LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia with Transformers:

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

pipe = pipeline("text-generation", model="LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia")
model = AutoModelForCausalLM.from_pretrained("LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia

SGLang

How to use LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia 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 "LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia" \
    --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": "LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia",
		"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 "LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia" \
        --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": "LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia with Docker Model Runner:
```
docker model run hf.co/LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia
```

Mythologic 7b trained with the synthia dataset

In my experience you can either get very detailed responses or very short reponses, you might have to tweak around the amount of generation lol

Downloads last month: 7

LTC-AI-Labs
/

L2-7b-Mini-Mythologic-Synthia

Dataset used to train LTC-AI-Labs/L2-7b-Mini-Mythologic-Synthia