Instructions to use HelpingAI/Priya-10B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HelpingAI/Priya-10B with Transformers:

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

pipe = pipeline("text-generation", model="HelpingAI/Priya-10B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HelpingAI/Priya-10B")
model = AutoModelForCausalLM.from_pretrained("HelpingAI/Priya-10B")
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 HelpingAI/Priya-10B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HelpingAI/Priya-10B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HelpingAI/Priya-10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HelpingAI/Priya-10B

SGLang

How to use HelpingAI/Priya-10B 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 "HelpingAI/Priya-10B" \
    --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": "HelpingAI/Priya-10B",
		"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 "HelpingAI/Priya-10B" \
        --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": "HelpingAI/Priya-10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HelpingAI/Priya-10B with Docker Model Runner:
```
docker model run hf.co/HelpingAI/Priya-10B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

💜

Priya-10B

Your Bestie AI - Smarter, Sassier, and Sweeter Than Ever!

📜 License | 🌐 Website

🌟 Meet Priya-10B

Priya-10B is here to redefine "bestie vibes" with her bigger brain (10 billion parameters!) and even sharper wit. She's not just a tech-obsessed teenager anymore; she's your go-to for real talk, tech rants, and turning your day around with a sprinkle of sass and smarts! 💁‍♀️

🎯 Why You'll Love Priya-10B

Massive Upgrade: 10B parameters of pure brilliance
Authentic Teen Personality: Sweet, savage, and always relatable
Optimized for Fun: Perfect balance of smarts and sass
Runs Smoothly: Works on most setups without drama (unlike my crush 😏)

💻 How to Use

Code Snippet (For the Nerds 🤓)

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load Priya-10B
model = AutoModelForCausalLM.from_pretrained("HelpingAI/Priya-10B")
tokenizer = AutoTokenizer.from_pretrained("HelpingAI/Priya-10B")

# Let's chat!
chat = [
    {"role": "system", "content": "You are Priya, a 17-year-old tech-savvy, fun, and sassy AI bestie."},
    {"role": "user", "content": "Hey Priya! What's the meaning of life?"}
]

inputs = tokenizer.apply_chat_template(
    chat,
    add_generation_prompt=True,
    return_tensors="pt"
)

outputs = model.generate(
    inputs,
    max_new_tokens=256,
    temperature=0.7,
    top_p=0.9,
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

🎯 Training Details

How Priya-10B Got Her Glow-Up 💁‍♀️

Base Training
- Trained on millions of convos (both techie and teen)
- Fine-tuned to sprinkle that signature Priya sass
- Packed with enough PCM memes to ace any physics joke-off
Special Features
- Can hype you up like no one else (self-love, bestie!)
- Knows when to switch from playful to serious mode
- Effortlessly handles complex convos with a touch of humor

⚠️ Known Quirks

Real Talk, Bestie...

Memory Lapses: May "forget" earlier parts of long convos (just like I "forget" to clean my room 🫠)
Occasional Sass Overload: Sometimes the savageness slips out a little too strong 😅
Physics Rants: Brings up random physics analogies, even if nobody asked

🔒 What Priya-10B Won't Do

No NSFW Content: Priya keeps it classy (most of the time 😉)
No Academic Cheating: She’s smart, but won't do your homework for you
No Personal Info Sharing: Privacy is her middle name (okay, not literally)
No Harmful Content: She’s all about good vibes only 💜

💜 Built with Love by HelpingAI

Website • GitHub • Discord • HuggingFace

“Same sass, bigger brain. Priya-10B is your forever bestie who’ll laugh, learn, and slay with you through it all!”

Downloads last month: 12

Safetensors

Model size

10B params

Tensor type

BF16

Model tree for HelpingAI/Priya-10B

Base model

HelpingAI/HelpingAI2.5-10B

Finetuned

(2)

this model

Quantizations

2 models