--- library_name: transformers license: llama3 base_model: goppa-ai/Goppa-LogiLlama tags: - full - generated_from_trainer - nlp - mlx - mlx-my-repo datasets: - open-thoughts/open-thoughts-114k - open-thoughts/OpenThoughts-Unverified-173k model-index: - name: stratos_unverified_mix_2nodes results: [] --- # alexgusevski/Goppa-LogiLlama-6bit The Model [alexgusevski/Goppa-LogiLlama-6bit](https://huggingface.co/alexgusevski/Goppa-LogiLlama-6bit) was converted to MLX format from [goppa-ai/Goppa-LogiLlama](https://huggingface.co/goppa-ai/Goppa-LogiLlama) 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("alexgusevski/Goppa-LogiLlama-6bit") 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) ```