| language: | |
| - en | |
| - ko | |
| license: cc-by-nc-4.0 | |
| tags: | |
| - dnotitia | |
| - nlp | |
| - llm | |
| - slm | |
| - conversation | |
| - chat | |
| - reasoning | |
| - r1 | |
| - mlx | |
| - mlx-my-repo | |
| base_model: dnotitia/DNA-R1 | |
| library_name: transformers | |
| pipeline_tag: text-generation | |
| # KYUNGYONG/DNA-R1-8bit | |
| The Model [KYUNGYONG/DNA-R1-8bit](https://huggingface.co/KYUNGYONG/DNA-R1-8bit) was converted to MLX format from [dnotitia/DNA-R1](https://huggingface.co/dnotitia/DNA-R1) using mlx-lm version **0.21.5**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("KYUNGYONG/DNA-R1-8bit") | |
| 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) | |
| ``` | |