Instructions to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF",
	filename="chocolatine-3b-instruct-dpo-v1.2-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF 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 jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M

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 jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M

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 jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M

SGLang

How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF 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 "jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF" \
    --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": "jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF",
		"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 "jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF" \
        --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": "jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF 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 jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF 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 jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF / README.md

jpacifico

Update README.md

e422449 verified over 1 year ago

preview code

Raw

History Blame

1.56 kB

	---
	base_model: jpacifico/Chocolatine-3B-Instruct-DPO-v1.2
	datasets:
	- jpacifico/french-orca-dpo-pairs-revised
	language:
	- fr
	- en
	library_name: transformers
	license: mit
	pipeline_tag: text-generation
	tags:
	- french
	- chocolatine
	- llama-cpp
	---

	# Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF

	Quantized q4_k_m GGUF version of the original model [`jpacifico/Chocolatine-3B-Instruct-DPO-v1.2`](https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2)
	can be used on a CPU device, compatible [llama.cpp](https://github.com/ggerganov/llama.cpp)
	now supported architecture by [LM Studio](https://lmstudio.ai/).
	Also ready for Raspberry Pi 5 8Gb.

	The model supports 128K context length.

	### Ollama

	[jpacifico/chocolatine-3b](https://ollama.com/jpacifico/chocolatine-3b)

	Usage:

	```bash
	ollama run jpacifico/chocolatine-3b
	```

	Ollama Modelfile example :

	```bash
	FROM ./chocolatine-3b-instruct-dpo-v1.2-q4_k_m.gguf
	TEMPLATE """{{ if .System }}<\|system\|>
	{{ .System }}<\|end\|>
	{{ end }}{{ if .Prompt }}<\|user\|>
	{{ .Prompt }}<\|end\|>
	{{ end }}<\|assistant\|>
	{{ .Response }}<\|end\|>
	"""
	PARAMETER stop """{"stop": ["<\|end\|>","<\|user\|>","<\|assistant\|>"]}"""
	SYSTEM """You are a friendly assistant called Chocolatine."""
	```


	### Limitations

	The Chocolatine model is a quick demonstration that a base model can be easily fine-tuned to achieve compelling performance.
	It does not have any moderation mechanism.

	- Developed by: Jonathan Pacifico, 2024
	- Model type: LLM
	- Language(s) (NLP): French, English
	- License: MIT