---
license: apache-2.0
language:
- th
- zh
- en
metrics:
- accuracy
base_model: nectec/Pathumma-llm-text-1.0.0
base_model_relation: finetune
pipeline_tag: text-generation
tags:
- chemistry
- biology
- finance
- legal
- code
- medical
- text-generation-inference
- mlx
- mlx-my-repo
---

# tawankri/Pathumma-llm-text-1.0.0-mlx-8Bit

The Model [tawankri/Pathumma-llm-text-1.0.0-mlx-8Bit](https://huggingface.co/tawankri/Pathumma-llm-text-1.0.0-mlx-8Bit) was converted to MLX format from [nectec/Pathumma-llm-text-1.0.0](https://huggingface.co/nectec/Pathumma-llm-text-1.0.0) using mlx-lm version **0.22.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("tawankri/Pathumma-llm-text-1.0.0-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)
```