Instructions to use Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3 with Transformers:

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

pipe = pipeline("text-generation", model="Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3")
model = AutoModelForCausalLM.from_pretrained("Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3

SGLang

How to use Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3 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 "Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3" \
    --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": "Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3",
		"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 "Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3" \
        --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": "Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3 with Docker Model Runner:
```
docker model run hf.co/Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Alpha version for the French Pro model

Suitable model for professional use

Dataset

Selected French professional dataset

Tuning

Use specific receipices with QLora methods

This model is under construction

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	17.50
IFEval (0-Shot)	50.83
BBH (3-Shot)	16.67
MATH Lvl 5 (4-Shot)	1.06
GPQA (0-shot)	2.01
MuSR (0-shot)	12.31
MMLU-PRO (5-shot)	22.12

Downloads last month: 11

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3

Quantizations

2 models

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

50.830
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

16.670
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

1.060
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

2.010
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

12.310
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

22.120