| language: | |
| - en | |
| license: apache-2.0 | |
| base_model: FutureMa/Eva-4B | |
| tags: | |
| - finance | |
| - earnings-calls | |
| - financial-nlp | |
| - text-classification | |
| - qwen3 | |
| - llm-as-judge | |
| - distillation | |
| - mlx | |
| - mlx-my-repo | |
| pipeline_tag: text-generation | |
| library_name: transformers | |
| spaces: | |
| - FutureMa/financial-evasion-detection | |
| # alexgusevski/Eva-4B-mlx-2Bit | |
| The Model [alexgusevski/Eva-4B-mlx-2Bit](https://huggingface.co/alexgusevski/Eva-4B-mlx-2Bit) was converted to MLX format from [FutureMa/Eva-4B](https://huggingface.co/FutureMa/Eva-4B) using mlx-lm version **0.29.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("alexgusevski/Eva-4B-mlx-2Bit") | |
| 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) | |
| ``` | |