| license: mit | |
| library_name: mlx | |
| datasets: | |
| - PrimeIntellect/verifiable-coding-problems | |
| - likaixin/TACO-verified | |
| - livecodebench/code_generation_lite | |
| language: | |
| - en | |
| base_model: mlx-community/DeepCoder-14B-Preview-8bit | |
| pipeline_tag: text-generation | |
| tags: | |
| - mlx | |
| - mlx | |
| - mlx-my-repo | |
| # introvoyz041/DeepCoder-14B-Preview-8bit-mlx-8Bit | |
| The Model [introvoyz041/DeepCoder-14B-Preview-8bit-mlx-8Bit](https://huggingface.co/introvoyz041/DeepCoder-14B-Preview-8bit-mlx-8Bit) was converted to MLX format from [mlx-community/DeepCoder-14B-Preview-8bit](https://huggingface.co/mlx-community/DeepCoder-14B-Preview-8bit) using mlx-lm version **0.28.3**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("introvoyz041/DeepCoder-14B-Preview-8bit-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) | |
| ``` | |