boatchrnthn's picture
Upload folder using huggingface_hub
9fb23cf verified
|
Raw History Blame Contribute Delete
1.07 kB
---
license: apache-2.0
language:
- th
- en
base_model: typhoon-ai/typhoon-ocr2-2b
base_model_relation: finetune
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- ocr
- document-parsing
- layout-analysis
- table-recognition
- thai
- mlx
- mlx-my-repo
---
# boatchrnthn/typhoon-ocr2-2b-mlx-4Bit
The Model [boatchrnthn/typhoon-ocr2-2b-mlx-4Bit](https://huggingface.co/boatchrnthn/typhoon-ocr2-2b-mlx-4Bit) was converted to MLX format from [typhoon-ai/typhoon-ocr2-2b](https://huggingface.co/typhoon-ai/typhoon-ocr2-2b) using mlx-lm version **0.31.2**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("boatchrnthn/typhoon-ocr2-2b-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)
```