Instructions to use Ont/Marcoroni-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ont/Marcoroni-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ont/Marcoroni-13B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ont/Marcoroni-13B") model = AutoModelForCausalLM.from_pretrained("Ont/Marcoroni-13B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ont/Marcoroni-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ont/Marcoroni-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ont/Marcoroni-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ont/Marcoroni-13B
- SGLang
How to use Ont/Marcoroni-13B 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 "Ont/Marcoroni-13B" \ --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": "Ont/Marcoroni-13B", "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 "Ont/Marcoroni-13B" \ --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": "Ont/Marcoroni-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Ont/Marcoroni-13B with Docker Model Runner:
docker model run hf.co/Ont/Marcoroni-13B
|
Download README.md from Ont/Marcoroni-13B: direct link, hf CLI and curl.
- Browser
- Download file 1.1 kB
-
https://huggingface.co/Ont/Marcoroni-13B/resolve/main/README.md
- Command line
-
hf download hf://Ont/Marcoroni-13B/README.md
-
curl -L -o README.md https://huggingface.co/Ont/Marcoroni-13B/resolve/main/README.md
1.1 kB
metadata
license: cc-by-nc-4.0
datasets:
- Open-Orca/OpenOrca
language:
- en
pipeline_tag: text-generation
Marcoroni-13B - Safetensors
A conversion of the original model [AIDC-ai-business/Marcoroni-13B] to safetensors format.
Marcoroni-13B
Model Details
- Trained by: trained by AIDC AI-Business.
- Model type: Marcoroni-13B is an auto-regressive language model based on the Llama 2 transformer architecture.
- Language(s): English
- License for Marcoroni-13B base weights: Non-Commercial Creative Commons license (CC BY-NC-4.0)
Prompting
Prompt Template for alpaca style
### Instruction:
<prompt> (without the <>)
### Response:
Evaluation Results (Open LLM Leaderboard)
| Metric | Value |
|---|---|
| Avg. | 65.76 |
| ARC (25-shot) | 62.46 |
| HellaSwag (10-shot) | 83.27 |
| MMLU (5-shot) | 59.63 |
| TruthfulQA (0-shot) | 57.7 |