Text Generation
MLX
Safetensors
Portuguese
llama
quantized
portuguese
european-portuguese
amalia
conversational
8-bit precision
Instructions to use layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit 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("layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit") 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) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
|
Download README.md from layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit: direct link, hf CLI and curl.
- Browser
- Download file 1.64 kB
-
https://huggingface.co/layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit/resolve/main/README.md
- Command line
-
hf download hf://layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit/README.md
-
curl -L -o README.md https://huggingface.co/layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit/resolve/main/README.md
1.64 kB
metadata
license: apache-2.0
language:
- pt
base_model:
- amalia-llm/AMALIA-9B-0626-DPO
base_model_relation: quantized
pipeline_tag: text-generation
library_name: mlx
tags:
- mlx
- quantized
- portuguese
- european-portuguese
- amalia
AMALIA-9B-0626-DPO — MLX 8-bit
8-bit MLX quantization of amalia-llm/AMALIA-9B-0626-DPO (~9.7 GB), for Apple Silicon Macs via mlx-lm.
AMALIA is an open-source language model targeting European Portuguese, developed by a consortium of Portuguese universities and research centres and funded by the Government of Portugal. This is the DPO (preference-tuned) variant. See the original model card and the technical report for full details.
Converted with mlx_lm.convert (8-bit, group size 64).
Usage
pip install mlx-lm
mlx_lm.generate --model layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit --prompt "Explica o que é o Arquivo.pt."
# or chat
mlx_lm.chat --model layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit
from mlx_lm import load, generate
model, tokenizer = load("layerx-labs/AMALIA-9B-0626-DPO-MLX-8bit")
prompt = tokenizer.apply_chat_template([{"role": "user", "content": "Explica o que é o Arquivo.pt."}], add_generation_prompt=True, tokenize=False)
print(generate(model, tokenizer, prompt=prompt, max_tokens=256))
License
Apache 2.0, same as the original model. All credit for the model goes to the AMALIA project.