Instructions to use piyushgaba07/MAYA_Llama_2_7b_quantized_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use piyushgaba07/MAYA_Llama_2_7b_quantized_model with Transformers:

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

pipe = pipeline("text-generation", model="piyushgaba07/MAYA_Llama_2_7b_quantized_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("piyushgaba07/MAYA_Llama_2_7b_quantized_model")
model = AutoModelForCausalLM.from_pretrained("piyushgaba07/MAYA_Llama_2_7b_quantized_model")
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 Settings

vLLM

How to use piyushgaba07/MAYA_Llama_2_7b_quantized_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "piyushgaba07/MAYA_Llama_2_7b_quantized_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "piyushgaba07/MAYA_Llama_2_7b_quantized_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/piyushgaba07/MAYA_Llama_2_7b_quantized_model

SGLang

How to use piyushgaba07/MAYA_Llama_2_7b_quantized_model 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 "piyushgaba07/MAYA_Llama_2_7b_quantized_model" \
    --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": "piyushgaba07/MAYA_Llama_2_7b_quantized_model",
		"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 "piyushgaba07/MAYA_Llama_2_7b_quantized_model" \
        --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": "piyushgaba07/MAYA_Llama_2_7b_quantized_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use piyushgaba07/MAYA_Llama_2_7b_quantized_model with Docker Model Runner:
```
docker model run hf.co/piyushgaba07/MAYA_Llama_2_7b_quantized_model
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

🧠 LLaMA 2 7B - Mental Therapy (Quantized, Instruction-Tuned)

Welcome to the repository for the LLaMA 2 7B Mental Therapy Quantized model — a safe and supportive conversational AI fine-tuned on mental health and therapy-related dialogues. Built on Meta’s LLaMA 2 7B, this model has been trained to generate empathetic, context-aware, and non-judgmental responses for users seeking emotional support and motivation.

⚠️ This model is not a replacement for professional mental health care. Use responsibly and always consult a licensed expert in case of serious mental health concerns.

💡 Model Highlights

🔧 Base model: meta-llama/Llama-2-7b-hf
🧠 Fine-tuning objective: Mental health and supportive conversation
🧱 Quantization: 4-bit (QLoRA) using bitsandbytes
🧾 Instruction format: Chat-like structure with ### User and ### Assistant prompts
🔐 Safe & empathetic responses: Fine-tuned with filtered mental health-related corpora
🚫 Very low toxicity: Evaluated with Detoxify and manual audits

🧪 Intended Use

This model is ideal for:

Emotional wellness chatbots
AI journaling assistants
Motivational and CBT-style coaching tools
Empathetic conversational agents for non-critical use

It is not suitable for:

Diagnosing or treating mental illnesses
Emergency or crisis intervention
Replacing human therapists or counselors

🚀 How to Use

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "your-username/llama-2-7b-mental-therapy-quantized"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.float16
)

prompt = """### User: I'm feeling overwhelmed and anxious all the time. What should I do?
### Assistant:"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(response)

Downloads last month: 8

Safetensors

Model size

7B params

Tensor type

I32

F16