license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
base_model: huihui-ai/Huihui-Qwythos-9B-Claude-Mythos-5-1M-abliterated
tags: - qwen3.5
- reasoning
- uncensored
- long-context
- 1M-context
- function-calling
- tool-use
- sft
- full-fine-tune
- cybersecurity
- biomedical
- agentic
- abliterated
- mlx
- mlx-my-repo
keXjos/Huihui-Qwythos-9B-Claude-Mythos-5-1M-abliterated-mlx-8Bit
The Model keXjos/Huihui-Qwythos-9B-Claude-Mythos-5-1M-abliterated-mlx-8Bit was converted to MLX format from huihui-ai/Huihui-Qwythos-9B-Claude-Mythos-5-1M-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-Qwythos-9B-Claude-Mythos-5-1M-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)