Instructions to use zamal/gemma-7b-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zamal/gemma-7b-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="zamal/gemma-7b-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zamal/gemma-7b-finetuned")
model = AutoModelForCausalLM.from_pretrained("zamal/gemma-7b-finetuned")
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 zamal/gemma-7b-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zamal/gemma-7b-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zamal/gemma-7b-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zamal/gemma-7b-finetuned

SGLang

How to use zamal/gemma-7b-finetuned 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 "zamal/gemma-7b-finetuned" \
    --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": "zamal/gemma-7b-finetuned",
		"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 "zamal/gemma-7b-finetuned" \
        --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": "zamal/gemma-7b-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zamal/gemma-7b-finetuned with Docker Model Runner:
```
docker model run hf.co/zamal/gemma-7b-finetuned
```

Fine-tuned Model for Prompt Enhancement ✍️

Overview

This model is fine-tuned using the QLORA (Quantized Low Rank Adaptation) approach, specifically designed to enhance textual prompts. The primary objective of this model is to take a user's initial prompt and refine it into the best possible version, optimizing clarity, engagement, and effectiveness. This capability makes it an invaluable tool for a wide range of applications, from improving chatbot interactions to enhancing creative writing processes.

Features

Prompt Optimization: Inputs an initial, potentially unrefined prompt and outputs a significantly improved version.
Broad Application: Suitable for content creators, marketers, developers creating interactive AI, and more.

How It Works

The model operates by analyzing the structure, content, and intent behind the input prompt. Using the QLORA fine-tuning methodology, it identifies areas for enhancement and generates a revised version that better captures the intended message or question, ensuring higher engagement and clearer communication.

Model input: "C program to add two numbers"
Improved Prompt as output:  "Implement a C program that takes two integer inputs and calculates their sum"

Model input: "I wanna learn Martial Arts"
Improved Prompt as output: "Explain the steps one would take to learn martial arts, from beginner to advanced levels."

Usage

This model can be accessed via the Hugging Face API or directly integrated into applications through our provided endpoints. Here's a simple example of how to use the model via the Hugging Face API:

import requests

API_URL = "/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fzamal%2Fgemma-7b-finetuned"
headers = {"Authorization": "Bearer <your-api-key>"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

output = query({
    "inputs": "Your initial prompt here",
})

print(output)

Downloads last month: 11

Safetensors

Model size

9B params

Tensor type

F32

zamal
/

gemma-7b-finetuned

Fine-tuned Model for Prompt Enhancement ✍️

Overview

Features

How It Works

Usage

Spaces using zamal/gemma-7b-finetuned 16