Instructions to use versae/filiberto-7B-instruct-exp1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use versae/filiberto-7B-instruct-exp1 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("versae/filiberto-7B-instruct-exp1")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use versae/filiberto-7B-instruct-exp1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="versae/filiberto-7B-instruct-exp1",
	filename="ggml-model-f16.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 versae/filiberto-7B-instruct-exp1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf versae/filiberto-7B-instruct-exp1:F16
# Run inference directly in the terminal:
llama-cli -hf versae/filiberto-7B-instruct-exp1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf versae/filiberto-7B-instruct-exp1:F16
# Run inference directly in the terminal:
llama-cli -hf versae/filiberto-7B-instruct-exp1: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 versae/filiberto-7B-instruct-exp1:F16
# Run inference directly in the terminal:
./llama-cli -hf versae/filiberto-7B-instruct-exp1: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 versae/filiberto-7B-instruct-exp1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf versae/filiberto-7B-instruct-exp1:F16

Use Docker

docker model run hf.co/versae/filiberto-7B-instruct-exp1:F16

LM Studio
Jan

vLLM

How to use versae/filiberto-7B-instruct-exp1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "versae/filiberto-7B-instruct-exp1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "versae/filiberto-7B-instruct-exp1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/versae/filiberto-7B-instruct-exp1:F16

Ollama
How to use versae/filiberto-7B-instruct-exp1 with Ollama:
```
ollama run hf.co/versae/filiberto-7B-instruct-exp1:F16
```

Unsloth Studio

How to use versae/filiberto-7B-instruct-exp1 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 versae/filiberto-7B-instruct-exp1 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 versae/filiberto-7B-instruct-exp1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for versae/filiberto-7B-instruct-exp1 to start chatting

MLX LM

How to use versae/filiberto-7B-instruct-exp1 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "versae/filiberto-7B-instruct-exp1"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "versae/filiberto-7B-instruct-exp1"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "versae/filiberto-7B-instruct-exp1",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use versae/filiberto-7B-instruct-exp1 with Docker Model Runner:
```
docker model run hf.co/versae/filiberto-7B-instruct-exp1:F16
```

Lemonade

How to use versae/filiberto-7B-instruct-exp1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull versae/filiberto-7B-instruct-exp1:F16

Run and chat with the model

lemonade run user.filiberto-7B-instruct-exp1-F16

List all available models

lemonade list

versae/filiberto-7B-instruct-exp1

This model was converted to MLX format from mistralai/Mistral-7B-Instruct-v0.2 using mlx-lm version 0.9.0. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate
model, tokenizer = load("versae/filiberto-7B-instruct-exp1")

OCR correction

text = """Otra vez, Don Iuan, me dad,
y otras mil vezes los braços.
Otra, y otras mil sean lazos
de nuestra antigua amistad.
Como venis?
Yo me siento
tan alegre, tan vfano,
tan venturoso, tan vano,
que no podrà el pensamiento
encareceros jamàs
las venturas que posseo,
porque el pensamiento creo"""

prompt = f"""<s>[INST] Dado el siguiente texto OCR, corrige los fallos que encuentres y devuelve el texto corregido:

{text} [/INST]"""

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Stanza identification

text = """Alcázares finjo más altos que montes;
escalo las bóvedas de ingrávido tul
asida a las ruedas de alados Faetones;
ensueño quimeras; oteo horizontes
de nieve, de rosa, de nácar, de azul."""

prompt = f"""<s>[INST] Indique el nombre de la siguiente estrofa:

{text} [/INST]"""

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Downloads last month: 8

Safetensors

Model size

7B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized