Model: mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16 Source: Original Platform
base_model, language, license, license_link, pipeline_tag, tags
| base_model | language | license | license_link | pipeline_tag | tags | |||
|---|---|---|---|---|---|---|---|---|
| Qwen/Qwen2.5-1.5B |
|
apache-2.0 | https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE | text-generation |
|
mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16
The Model mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16 was converted to MLX format from Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 using mlx-lm version 0.13.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Description
Model synced from source: mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16