Instructions to use Abhaykoul/HelpingAI2.5-prototype-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abhaykoul/HelpingAI2.5-prototype-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Abhaykoul/HelpingAI2.5-prototype-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Abhaykoul/HelpingAI2.5-prototype-v2")
model = AutoModelForCausalLM.from_pretrained("Abhaykoul/HelpingAI2.5-prototype-v2")
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 Abhaykoul/HelpingAI2.5-prototype-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abhaykoul/HelpingAI2.5-prototype-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abhaykoul/HelpingAI2.5-prototype-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abhaykoul/HelpingAI2.5-prototype-v2

SGLang

How to use Abhaykoul/HelpingAI2.5-prototype-v2 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 "Abhaykoul/HelpingAI2.5-prototype-v2" \
    --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": "Abhaykoul/HelpingAI2.5-prototype-v2",
		"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 "Abhaykoul/HelpingAI2.5-prototype-v2" \
        --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": "Abhaykoul/HelpingAI2.5-prototype-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Abhaykoul/HelpingAI2.5-prototype-v2 with Docker Model Runner:
```
docker model run hf.co/Abhaykoul/HelpingAI2.5-prototype-v2
```

HelpingAI 2.5 Prototype

Overview

Welcome to the HelpingAI 2.5 Prototype! This model is designed to provide emotionally intelligent conversational AI experiences. By understanding user emotions and context, HelpingAI 2.5 aims to enhance human-computer interactions, making them more meaningful and engaging.

Key Features

Emotion Recognition: Understands user emotions for tailored responses.
Contextual Understanding: Adapts based on conversation history.
Multi-Domain Support: Suitable for various applications including customer support, education, and personal assistance.
User Feedback Integration: Continuously improves based on user interactions and feedback.

Demo

Experience the model in action! Visit our demo space to try out the HelpingAI 2.5 prototype.

Getting Involved

We’re eager to hear your thoughts! Feel free to provide feedback or report issues via discussion.

Future Plans

We are excited to announce that we will be re-releasing HelpingAI (3B, 3B Coder, and Flash) with a new personality and more human-like features on Diwali! Additionally, the HelpingAI 2.5 models will be available on November 17 🎉.

Acknowledgments

Hugging Face for providing an incredible platform for AI development.
The open-source community for their continuous support and contributions.

Join us in shaping the future of AI! 🤖💖

Downloads last month: 4

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for Abhaykoul/HelpingAI2.5-prototype-v2

Base model

HelpingAI/HelpingAI2-9B

Finetuned

(1)

this model