| library_name: transformers | |
| metrics: | |
| - code_eval | |
| tags: | |
| - code | |
| - mlx | |
| model-index: | |
| - name: WizardCoder | |
| results: | |
| - task: | |
| type: text-generation | |
| dataset: | |
| name: HumanEval | |
| type: openai_humaneval | |
| metrics: | |
| - type: pass@1 | |
| value: 0.799 | |
| name: pass@1 | |
| verified: false | |
| # ipetrukha/WizardCoder-33B-V1.1-4bit | |
| The Model [ipetrukha/WizardCoder-33B-V1.1-4bit](https://huggingface.co/ipetrukha/WizardCoder-33B-V1.1-4bit) was converted to MLX format from [WizardLMTeam/WizardCoder-33B-V1.1](https://huggingface.co/WizardLMTeam/WizardCoder-33B-V1.1) using mlx-lm version **0.16.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("ipetrukha/WizardCoder-33B-V1.1-4bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |