h3vasc's picture
Upload README.md with huggingface_hub
60eec16 verified
|
Raw History Blame Contribute Delete
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.