Instructions to use neovalle/H4rmoniousBreezeDPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neovalle/H4rmoniousBreezeDPO with Transformers:

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

pipe = pipeline("text-generation", model="neovalle/H4rmoniousBreezeDPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neovalle/H4rmoniousBreezeDPO")
model = AutoModelForCausalLM.from_pretrained("neovalle/H4rmoniousBreezeDPO")
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

vLLM

How to use neovalle/H4rmoniousBreezeDPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neovalle/H4rmoniousBreezeDPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neovalle/H4rmoniousBreezeDPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neovalle/H4rmoniousBreezeDPO

SGLang

How to use neovalle/H4rmoniousBreezeDPO 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 "neovalle/H4rmoniousBreezeDPO" \
    --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": "neovalle/H4rmoniousBreezeDPO",
		"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 "neovalle/H4rmoniousBreezeDPO" \
        --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": "neovalle/H4rmoniousBreezeDPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neovalle/H4rmoniousBreezeDPO with Docker Model Runner:
```
docker model run hf.co/neovalle/H4rmoniousBreezeDPO
```

Model Card for Model neovalle/H4rmoniousBreezeDPO

Model Details

Model Description

This is model is a version of HuggingFaceH4/zephyr-7b-beta fine-tuned via DPO, using the H4rmony_dpo dataset, which aims to better align the model with ecological values through the use of ecolinguistics principles.

Developed by: Jorge Vallego
Funded by : Neovalle Ltd.
Shared by : airesearch@neovalle.co.uk
Model type: mistral
Language(s) (NLP): Primarily English
License: MIT
Finetuned from model: HuggingFaceH4/zephyr-7b-beta

Uses

Intended as PoC to show the effects of H4rmony_dpo dataset with DPO fine-tuning..

Direct Use

For testing purposes to gain insight in order to help with the continous improvement of the H4rmony_dpo dataset.

Downstream Use

Its direct use in applications is not recommended as this model is under testing for a specific task only (Ecological Alignment)

Out-of-Scope Use

Not meant to be used other than testing and evaluation of the H4rmony dataset and ecological alignment.

Bias, Risks, and Limitations

This model might produce biased completions already existing in the base model, and others unintentionally introduced during fine-tuning.

How to Get Started with the Model

It can be loaded and run in a Colab instance with High RAM.

Training Details

Trained using DPO

Training Data

H4rmony Dataset - https://huggingface.co/datasets/neovalle/H4rmony_dpo

Downloads last month: 805

Safetensors

Model size

7B params

Tensor type

F16

neovalle
/

H4rmoniousBreezeDPO