| license: apache-2.0 | |
| language: | |
| - en | |
| - hi | |
| library_name: transformers | |
| tags: | |
| - text-to-speech | |
| - tts | |
| - hindi | |
| - english | |
| - llama | |
| - audio | |
| - speech | |
| - india | |
| - mlx | |
| - mlx-my-repo | |
| datasets: | |
| - proprietary | |
| pipeline_tag: text-to-speech | |
| co2_eq_emissions: | |
| emissions: 0 | |
| source: Not specified | |
| training_type: unknown | |
| geographical_location: unknown | |
| base_model: maya-research/Veena | |
| # hashvibe007/Veena-mlx-4Bit | |
| The Model [hashvibe007/Veena-mlx-4Bit](https://huggingface.co/hashvibe007/Veena-mlx-4Bit) was converted to MLX format from [maya-research/Veena](https://huggingface.co/maya-research/Veena) using mlx-lm version **0.22.3**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("hashvibe007/Veena-mlx-4Bit") | |
| 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) | |
| ``` | |