library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B/blob/main/LICENSE
pipeline_tag: text-generation
base_model: huihui-ai/Huihui-Qwen-AgentWorld-35B-A3B-abliterated
tags:
- qwen
- world-model
- agent
- environment-simulation
- abliterated
- uncensored
- huihui
- mlx
- mlx-my-repo
keXjos/Huihui-Qwen-AgentWorld-35B-A3B-abliterated-mlx-4Bit
The Model keXjos/Huihui-Qwen-AgentWorld-35B-A3B-abliterated-mlx-4Bit was converted to MLX format from huihui-ai/Huihui-Qwen-AgentWorld-35B-A3B-abliterated using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("keXjos/Huihui-Qwen-AgentWorld-35B-A3B-abliterated-mlx-4Bit")
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)