Instructions to use Neuronovo/neuronovo-9B-v0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neuronovo/neuronovo-9B-v0.4 with Transformers:

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

pipe = pipeline("text-generation", model="Neuronovo/neuronovo-9B-v0.4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neuronovo/neuronovo-9B-v0.4")
model = AutoModelForCausalLM.from_pretrained("Neuronovo/neuronovo-9B-v0.4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Neuronovo/neuronovo-9B-v0.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neuronovo/neuronovo-9B-v0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neuronovo/neuronovo-9B-v0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Neuronovo/neuronovo-9B-v0.4

SGLang

How to use Neuronovo/neuronovo-9B-v0.4 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 "Neuronovo/neuronovo-9B-v0.4" \
    --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": "Neuronovo/neuronovo-9B-v0.4",
		"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 "Neuronovo/neuronovo-9B-v0.4" \
        --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": "Neuronovo/neuronovo-9B-v0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Neuronovo/neuronovo-9B-v0.4 with Docker Model Runner:
```
docker model run hf.co/Neuronovo/neuronovo-9B-v0.4
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

More information about previous Neuronovo/neuronovo-9B-v0.2 version available here: 🔗Don't stop DPOptimizing!

Author: Jan Kocoń 🔗LinkedIn 🔗Google Scholar 🔗ResearchGate

Changes concerning Neuronovo/neuronovo-9B-v0.2:

Training Dataset: In addition to the Intel/orca_dpo_pairs dataset, this version incorporates a mlabonne/chatml_dpo_pairs. The combined datasets enhance the model's capabilities in dialogues and interactive scenarios, further specializing it in natural language understanding and response generation.
Tokenizer and Formatting: The tokenizer now originates directly from the Neuronovo/neuronovo-9B-v0.2 model.
Training Configuration: The training approach has shifted from using max_steps=200 to num_train_epochs=1. This represents a change in the training strategy, focusing on epoch-based training rather than a fixed number of steps.
Learning Rate: The learning rate has been reduced to a smaller value of 5e-8. This finer learning rate allows for more precise adjustments during the training process, potentially leading to better model performance.

Downloads last month: 206

Safetensors

Model size

9B params

Tensor type

F32

Model tree for Neuronovo/neuronovo-9B-v0.4

Quantizations

1 model

Neuronovo
/

neuronovo-9B-v0.4

Model tree for Neuronovo/neuronovo-9B-v0.4

Datasets used to train Neuronovo/neuronovo-9B-v0.4