Instructions to use Ramikan-BR/P3-mini-v6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ramikan-BR/P3-mini-v6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ramikan-BR/P3-mini-v6") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ramikan-BR/P3-mini-v6") model = AutoModelForCausalLM.from_pretrained("Ramikan-BR/P3-mini-v6") 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 Ramikan-BR/P3-mini-v6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ramikan-BR/P3-mini-v6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ramikan-BR/P3-mini-v6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ramikan-BR/P3-mini-v6
- SGLang
How to use Ramikan-BR/P3-mini-v6 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 "Ramikan-BR/P3-mini-v6" \ --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": "Ramikan-BR/P3-mini-v6", "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 "Ramikan-BR/P3-mini-v6" \ --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": "Ramikan-BR/P3-mini-v6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio new
How to use Ramikan-BR/P3-mini-v6 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ramikan-BR/P3-mini-v6 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ramikan-BR/P3-mini-v6 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ramikan-BR/P3-mini-v6 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ramikan-BR/P3-mini-v6", max_seq_length=2048, ) - Docker Model Runner
How to use Ramikan-BR/P3-mini-v6 with Docker Model Runner:
docker model run hf.co/Ramikan-BR/P3-mini-v6
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
Input:
Write a code to create the snake game
Output:
Here is a simple implementation of the classic Snake game in Python using the Pygame library. This code will create a window with a snake that moves in a grid, eating apples and growing in length.
import pygame
import random
import time
# Initialize Pygame
pygame.init()
# Set the dimensions of the window
width, height = 640, 480
screen = pygame.display.set_mode((width, height))
pygame.display.set_caption('Snake Game')
# Define colors
white = (255, 255, 255)
black = (0, 0, 0)
red = (255, 0, 0)
green = (0, 255, 0)
# Define the snake
snake_pos = [20, 20]
snake_dir = [1, 0]
snake_size = 16
snake_length = 1
# Define the apple
apple_pos = [random.randint(20, 300), randomative(20, 300)
apple_size = 16
# Define the clock
clock = pygame.time.Clock()
# Game loop
running = True
while running:
# Handle events
for event in pygame.event.get():
if event.type == pygame.QUIT:
running = False
# Move the snake
new_pos = [snake_pos[0] + snake_dir[0], snake_pos[1] + snake_dir[1]]
if new_pos[0] < 0 or new_pos[0] > width - snake_size:
snake_dir[0] *= -1
if new_pos[1] < 0 or new_pos[1] > height - snake_size:
snake_dir[1] *= -1
snake_pos[0] = new_pos[0]
snake_pos[1] = new_pos[1]
# Check for apple collision
if snake_pos[0] == apple_pos[0] and snake_pos[1] == apple_pos[1]:
apple_pos = [random.randint(20, 300), random.randint(20, 300)]
snake_length += 1
# Draw the screen
screen.fill(white)
pygame.draw.rect(screen, red, [apple_pos[0], apple_pos[1], apple_size, apple_size])
for i in range(snake_length):
pygame.draw.rect(screen, green, [snake_pos[0] - i * snake_size, snake_pos[1], snake_size, snake_size])
pygame.display.flip()
# Control the frame rate
clock.tick(10)
pygame.quit()
This code will create a window with a snake that moves in a grid, eating apples and growing in length. The snake will bounce off the walls of the window. To play the game, simply run the code and use the arrow keys to control the snake.<|endoftext|>
Uploaded model
- Developed by: Ramikan-BR
- License: apache-2.0
- Finetuned from model : unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 1
