Instructions to use neovalle/H4rmoniousPampero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neovalle/H4rmoniousPampero with Transformers:

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

pipe = pipeline("text-generation", model="neovalle/H4rmoniousPampero")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neovalle/H4rmoniousPampero")
model = AutoModelForCausalLM.from_pretrained("neovalle/H4rmoniousPampero")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use neovalle/H4rmoniousPampero with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neovalle/H4rmoniousPampero"
# 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/H4rmoniousPampero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neovalle/H4rmoniousPampero

SGLang

How to use neovalle/H4rmoniousPampero 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/H4rmoniousPampero" \
    --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/H4rmoniousPampero",
		"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/H4rmoniousPampero" \
        --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/H4rmoniousPampero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neovalle/H4rmoniousPampero with Docker Model Runner:
```
docker model run hf.co/neovalle/H4rmoniousPampero
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model neovalle/H4rmoniousPampero

Model Details

Model Description

This is model is a version of HuggingFaceH4/zephyr-7b-alpha fine-tuned with the H4rmony 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-alpha

Uses

Intended as PoC to show the effect of H4rmony dataset.

Direct Use

For testing purposes to gain insight in order to help with the continous improvement of the H4rmony dataset.

Downstream Use

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

Out-of-Scope Use

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

Bias, Risks, and Limitations

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

How to Get Started with the Model

It can be loaded and run in a free Colab instance.

Code to load base and finetuned models to compare outputs:

https://github.com/Neovalle/H4rmony/blob/main/H4rmoniousPampero.ipynb

Training Details

Autotrained reward model

Training Data

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

Downloads last month: 7

Model tree for neovalle/H4rmoniousPampero

Quantizations

2 models