license: apache-2.0
language:
- en
base_model: huihui-ai/Huihui-Tongyi-DeepResearch-30B-A3B-abliterated
pipeline_tag: text-generation
library_name: transformers
tags: - abliterated
- uncensored
- mlx
- mlx-my-repo
jurejaklic/Huihui-Tongyi-DeepResearch-30B-A3B-abliterated-mlx-8Bit
The Model jurejaklic/Huihui-Tongyi-DeepResearch-30B-A3B-abliterated-mlx-8Bit was converted to MLX format from huihui-ai/Huihui-Tongyi-DeepResearch-30B-A3B-abliterated using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("jurejaklic/Huihui-Tongyi-DeepResearch-30B-A3B-abliterated-mlx-8Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)