Instructions to use andrijdavid/macaroni-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andrijdavid/macaroni-7b with Transformers:

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

pipe = pipeline("text-generation", model="andrijdavid/macaroni-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("andrijdavid/macaroni-7b")
model = AutoModelForCausalLM.from_pretrained("andrijdavid/macaroni-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use andrijdavid/macaroni-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andrijdavid/macaroni-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andrijdavid/macaroni-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/andrijdavid/macaroni-7b

SGLang

How to use andrijdavid/macaroni-7b 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 "andrijdavid/macaroni-7b" \
    --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": "andrijdavid/macaroni-7b",
		"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 "andrijdavid/macaroni-7b" \
        --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": "andrijdavid/macaroni-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use andrijdavid/macaroni-7b with Docker Model Runner:
```
docker model run hf.co/andrijdavid/macaroni-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Macaroni 7B

This is an experimental merge of pre-trained mistral language models with fblgit/UNA-TheBeagle-7b-v1.

Disclaimer

No Warranty: The Model is provided on an "AS IS" basis, without warranty of any kind. The entire risk as to the quality, performance and use of The Model is with the user.
Limitation of Liability: In no event shall the creator(s) of The Model be liable for any claim, damages, or other liability, whether in an action of contract, tort or otherwise, arising from, out of, or in connection with The Model or the use or other dealings in The Model.
Accuracy and Risks: The creator(s) do not warrant that The Model is free from errors or inaccuracies and disclaim any responsibility for any harm resulting from the use of The Model.
Use at Your Own Risk: Users are solely responsible for any consequences resulting from the use of The Model, including but not limited to any changes made to The Model by the user or the results produced by The Model.
Compliance with Laws: Users are solely responsible for ensuring that their use of The Model complies with all applicable laws, regulations, and policies.
Ethical Use: Users are encouraged to use The Model ethically and responsibly. The creator(s) disclaim any responsibility for misuse or unethical use of The Model.
Modifications: Any modifications made to The Model by third parties are the sole responsibility of the party making the modifications. The original creator(s) of The Model shall not be responsible for any modifications made by third parties.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.60
AI2 Reasoning Challenge (25-Shot)	73.12
HellaSwag (10-Shot)	88.17
MMLU (5-Shot)	64.58
TruthfulQA (0-shot)	68.76
Winogrande (5-shot)	84.37
GSM8k (5-shot)	68.61

Downloads last month: 194

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for andrijdavid/macaroni-7b

Quantizations

3 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

73.120
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.170
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.580
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

68.760
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

84.370
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

68.610