DeepHat V1 7B Heretic Abliterated Mlx 5Bit

from mlx_lm import load, generate

model, tokenizer = load("usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-5Bit")

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)

--- language: en tags: - obliteratus - abliteration - uncensored - obliterate - mlx - mlx-my-repo base_model: usermma/DeepHat-V1-7B-Heretic-Abliterated --- # usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-5Bit The Model [usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-5Bit](https://huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-5Bit) was converted to MLX format from [usermma/DeepHat-V1-7B-Heretic-Abliterated](https://huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated) using mlx-lm version **0.31.2**. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-5Bit") 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) ```