enikeev_-_Cotype-Nano-MLX-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Cotype-Nano-MLX - GGUF

• Model creator: https://huggingface.co/enikeev/
• Original model: https://huggingface.co/enikeev/Cotype-Nano-MLX/

Original model description:

library_name: transformers language:

• ru
• en pipeline_tag: text-generation license: other license_name: apache-2.0 license_link: https://huggingface.co/MTSAIR/Cotype-Nano/blob/main/Apache%20License%20MTS%20AI.docx base_model: MTSAIR/Cotype-Nano tags:
• mlx

---

enikeev/Cotype-Nano-MLX

The Model enikeev/Cotype-Nano-MLX was converted to MLX format from MTSAIR/Cotype-Nano using mlx-lm version 0.20.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("enikeev/Cotype-Nano-MLX")

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)