README.md

---
pipeline_tag: text-generation
inference: true
widget:
- text: 'Hello!'
  example_title: Hello world
  group: Python
library_name: transformers
---

This model is randomly initialized, using the config from [Qwen/Qwen-VL-Chat](https://huggingface.co/Qwen/Qwen-VL-Chat/blob/main/config.json) but with smaller size. 
Note the model is in float16.

Notable modifications:

```python
config.fp16 = True
config.hidden_size = 8
config.intermediate_size = 16
config.kv_channels = 4
config.num_attention_heads = 2
config.num_hidden_layers = 2
config.seq_length = 2048

config.visual  = {
    "heads": 2,
    "image_size": 448,
    "image_start_id": 151857,
    "layers": 2,
    "mlp_ratio": 1.0,
    "output_dim": 8,
    "patch_size": 14,
    "width": 8,
}
```

Also, we changed the visual model attention head dim. See `upload_model.py` for details.