Instructions to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m with Transformers:

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

pipe = pipeline("text-generation", model="jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16
# Run inference directly in the terminal:
llama cli -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16
# Run inference directly in the terminal:
llama cli -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16
# Run inference directly in the terminal:
./llama-cli -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16

Use Docker

docker model run hf.co/jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16

LM Studio
Jan

vLLM

How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16

SGLang

How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m 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 "jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m" \
    --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": "jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m",
		"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 "jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m" \
        --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": "jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m with Ollama:
```
ollama run hf.co/jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16
```

Unsloth Studio

How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m 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 jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m 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 jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m to start chatting

Docker Model Runner
How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m with Docker Model Runner:
```
docker model run hf.co/jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16
```

Lemonade

How to use jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m:F16

Run and chat with the model

lemonade run user.CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m-F16

List all available models

lemonade list

Atomic Chat

ChatPRG v0.2.1 Llama 3.1 8B 4bit q4_k_m (stable version)

Modelo pre-entrenado para dar a conocer a estudiantes y personas externas, los reglamentos de la Universidad nacional Pedro Ruiz Gallo de Lambayeque, Perú
Pre-trained model to make known to students and external people the regulations of the Pedro Ruiz Gallo National University of Lambayeque, Peru

Testing the model

Observations

El modelo puede responder en inglés y español, a pesar de haber sido entrenado solo con un dataset en inglés, pero aún no puedo confirmar eso, hasta que el modelo pase por mas pruebas.
The model can answer in English and Spanish, although it was train only with an English dataset, but I can't still confirm that, until it has pass more test.