Update README.md

README.md

@@ -1,78 +1,78 @@
----
-inference: false
-license: apache-2.0
----
-
-# Model Card
-
-<p align="center">
-  <img src="./icon.png" alt="Logo" width="350">
-</p>
-
-📖 [Technical report]() | 🏠 [Code]() | 🐰 [Demo](http://bunny.dataoptim.org/)
-This is Owlet-Phi-2.
-
-Owlet is a family of lightweight but powerful multimodal models. 
-
-We provide Owlet-phi-2, which is built upon [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) and [Phi-2](https://huggingface.co/microsoft/phi-2). 
-
-
-# Quickstart
-
-Here we show a code snippet to show you how to use the model with transformers.
-
-Before running the snippet, you need to install the following dependencies:
-
-```shell
-pip install torch transformers accelerate pillow decord
-```
-
-```python
-import torch
-import transformers
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from PIL import Image
-import warnings
-
-
-# disable some warnings
-transformers.logging.set_verbosity_error()
-transformers.logging.disable_progress_bar()
-warnings.filterwarnings('ignore')
-
-# set device
-device = 'cuda'  # or cpu
-torch.set_default_device(device)
-
-# create model
-print('Loading the model...')
-model = AutoModelForCausalLM.from_pretrained(
-    'phronetic-ai/owlet-phi-2',
-    torch_dtype=torch.float16, # float32 for cpu
-    device_map='auto',
-    trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained(
-    'phronetic-ai/owlet-phi-2',
-    trust_remote_code=True)
-
-print('Model loaded. Processing the query...')
-# text prompt
-prompt = 'What is happening in the video?'
-text = f"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\n{prompt} ASSISTANT:"
-text_chunks = [tokenizer(chunk).input_ids for chunk in text.split('<image>')]
-input_ids = torch.tensor(text_chunks[0] + [-200] + text_chunks[1], dtype=torch.long).unsqueeze(0).to(device)
-
-# image or video file path
-file_path = 'sample.mp4'
-input_tensor = model.process(file_path, model.config).to(model.device, dtype=model.dtype)
-
-# generate
-output_ids = model.generate(
-    input_ids,
-    images=input_tensor,
-    max_new_tokens=100,
-    use_cache=True)[0]
-
-print(f'Response: {tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()}')
-
-```
+---
+inference: false
+license: cc-by-4.0
+---
+
+# Model Card
+
+<p align="center">
+  <img src="./icon.png" alt="Logo" width="350">
+</p>
+
+📖 [Technical report]() | 🏠 [Code]() | 🐰 [Demo](http://bunny.dataoptim.org/)
+This is Owlet-Phi-2.
+
+Owlet is a family of lightweight but powerful multimodal models. 
+
+We provide Owlet-phi-2, which is built upon [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) and [Phi-2](https://huggingface.co/microsoft/phi-2). 
+
+
+# Quickstart
+
+Here we show a code snippet to show you how to use the model with transformers.
+
+Before running the snippet, you need to install the following dependencies:
+
+```shell
+pip install torch transformers accelerate pillow decord
+```
+
+```python
+import torch
+import transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from PIL import Image
+import warnings
+
+
+# disable some warnings
+transformers.logging.set_verbosity_error()
+transformers.logging.disable_progress_bar()
+warnings.filterwarnings('ignore')
+
+# set device
+device = 'cuda'  # or cpu
+torch.set_default_device(device)
+
+# create model
+print('Loading the model...')
+model = AutoModelForCausalLM.from_pretrained(
+    'phronetic-ai/owlet-phi-2',
+    torch_dtype=torch.float16, # float32 for cpu
+    device_map='auto',
+    trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(
+    'phronetic-ai/owlet-phi-2',
+    trust_remote_code=True)
+
+print('Model loaded. Processing the query...')
+# text prompt
+prompt = 'What is happening in the video?'
+text = f"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\n{prompt} ASSISTANT:"
+text_chunks = [tokenizer(chunk).input_ids for chunk in text.split('<image>')]
+input_ids = torch.tensor(text_chunks[0] + [-200] + text_chunks[1], dtype=torch.long).unsqueeze(0).to(device)
+
+# image or video file path
+file_path = 'sample.mp4'
+input_tensor = model.process(file_path, model.config).to(model.device, dtype=model.dtype)
+
+# generate
+output_ids = model.generate(
+    input_ids,
+    images=input_tensor,
+    max_new_tokens=100,
+    use_cache=True)[0]
+
+print(f'Response: {tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()}')
+
+```