Adding usage and preprocessing script

README.md

@@ -25,7 +25,48 @@ This model has not been assessed for harm or biases, and should not be used for
 
 ## How to Get Started with the Model
 
-Using the LLaVA-Gemma models currently requires a custom fork of the [`LLaVA`](https://github.com/haotian-liu/LLaVA) library. _We will release converted checkpoints compatible with the HuggingFace implementation of LLaVA shortly._
+Currently using `llava-gemma` requires a [modified preprocessor](/processing_llavagemma.py).
+
+For example usage, see [`usage.py`](/usage.py) or the following code block:
+
+
+```python
+import requests
+from PIL import Image
+from transformers import (
+  LlavaForConditionalGeneration,
+  AutoTokenizer,
+  CLIPImageProcessor
+)
+from processing_llavagemma import LlavaGemmaProcessor # This is in this repo
+
+checkpoint = "Intel/llava-gemma-2b"
+
+# Load model
+model = LlavaForConditionalGeneration.from_pretrained(checkpoint)
+processor = LlavaGemmaProcessor(
+    tokenizer=AutoTokenizer.from_pretrained(checkpoint),
+    image_processor=CLIPImageProcessor.from_pretrained(checkpoint)
+)
+
+# Prepare inputs
+# Use gemma chat template
+prompt = processor.tokenizer.apply_chat_template(
+    [{'role': 'user', 'content': "What's the content of the image?<image>"}],
+    tokenize=False,
+    add_generation_prompt=True
+)
+url = "https://www.ilankelman.org/stopsigns/australia.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+inputs = processor(text=prompt, images=image, return_tensors="pt")
+inputs = {k: v.to('cuda') for k, v in inputs.items()}
+      
+# Generate
+generate_ids = model.generate(**inputs, max_length=30)
+output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+print(output)
+
+```
 
 
 

processing_llavagemma.py

@@ -0,0 +1,138 @@
+# coding=utf-8
+# Copyright 2023 The HuggingFace Inc. team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Processor class for Llava.
+Modified to include support for Gemma tokenizer.
+"""
+
+
+from typing import List, Optional, Union
+
+from transformers.feature_extraction_utils import BatchFeature
+from transformers.image_utils import ImageInput
+from transformers.processing_utils import ProcessorMixin
+from transformers.tokenization_utils_base import PaddingStrategy, PreTokenizedInput, TextInput, TruncationStrategy
+from transformers.utils import TensorType
+
+
+class LlavaGemmaProcessor(ProcessorMixin):
+    r"""
+    Constructs a Llava processor which wraps a Llava image processor and a Llava tokenizer into a single processor.
+
+    [`LlavaProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`LlamaTokenizerFast`]. See the
+    [`~LlavaProcessor.__call__`] and [`~LlavaProcessor.decode`] for more information.
+
+    Args:
+        image_processor ([`CLIPImageProcessor`], *optional*):
+            The image processor is a required input.
+        tokenizer ([`LlamaTokenizerFast`], *optional*):
+            The tokenizer is a required input.
+    """
+
+    attributes = ["image_processor", "tokenizer"]
+    image_processor_class = "CLIPImageProcessor"
+    tokenizer_class = ("LlamaTokenizer", "LlamaTokenizerFast",
+                       "GemmaTokenizer", "GemmaTokenizerFast")
+
+    def __init__(self, image_processor=None, tokenizer=None):
+        super().__init__(image_processor, tokenizer)
+
+    def __call__(
+        self,
+        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
+        images: ImageInput = None,
+        padding: Union[bool, str, PaddingStrategy] = False,
+        truncation: Union[bool, str, TruncationStrategy] = None,
+        max_length=None,
+        return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
+    ) -> BatchFeature:
+        """
+        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
+        and `kwargs` arguments to LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`] if `text` is not `None` to encode
+        the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
+        CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
+        of the above two methods for more information.
+
+        Args:
+            text (`str`, `List[str]`, `List[List[str]]`):
+                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
+                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
+                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
+            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
+                The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
+                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
+                number of channels, H and W are image height and width.
+            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
+                Select a strategy to pad the returned sequences (according to the model's padding side and padding
+                index) among:
+                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
+                  sequence if provided).
+                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
+                  acceptable input length for the model if that argument is not provided.
+                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
+                  lengths).
+            max_length (`int`, *optional*):
+                Maximum length of the returned list and optionally padding length (see above).
+            truncation (`bool`, *optional*):
+                Activates truncation to cut input sequences longer than `max_length` to `max_length`.
+            return_tensors (`str` or [`~utils.TensorType`], *optional*):
+                If set, will return tensors of a particular framework. Acceptable values are:
+
+                - `'tf'`: Return TensorFlow `tf.constant` objects.
+                - `'pt'`: Return PyTorch `torch.Tensor` objects.
+                - `'np'`: Return NumPy `np.ndarray` objects.
+                - `'jax'`: Return JAX `jnp.ndarray` objects.
+
+        Returns:
+            [`BatchFeature`]: A [`BatchFeature`] with the following fields:
+
+            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
+            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
+              `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
+              `None`).
+            - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
+        """
+        if images is not None:
+            pixel_values = self.image_processor(images, return_tensors=return_tensors)["pixel_values"]
+        else:
+            pixel_values = None
+        text_inputs = self.tokenizer(
+            text, return_tensors=return_tensors, padding=padding, truncation=truncation, max_length=max_length
+        )
+
+        return BatchFeature(data={**text_inputs, "pixel_values": pixel_values})
+
+    # Copied from transformers.models.clip.processing_clip.CLIPProcessor.batch_decode with CLIP->Llama
+    def batch_decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
+        refer to the docstring of this method for more information.
+        """
+        return self.tokenizer.batch_decode(*args, **kwargs)
+
+    # Copied from transformers.models.clip.processing_clip.CLIPProcessor.decode with CLIP->Llama
+    def decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
+        the docstring of this method for more information.
+        """
+        return self.tokenizer.decode(*args, **kwargs)
+
+    @property
+    # Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names
+    def model_input_names(self):
+        tokenizer_input_names = self.tokenizer.model_input_names
+        image_processor_input_names = self.image_processor.model_input_names
+        return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))

usage.py

@@ -0,0 +1,38 @@
+import transformers
+
+print(transformers.__version__)
+
+import requests
+from PIL import Image
+from transformers import (
+  LlavaForConditionalGeneration,
+  AutoTokenizer,
+  CLIPImageProcessor
+)
+from processing_llavagemma import LlavaGemmaProcessor
+
+checkpoint = "Intel/llava-gemma-2b"
+
+model = LlavaForConditionalGeneration.from_pretrained(checkpoint)
+processor = LlavaGemmaProcessor(
+    tokenizer=AutoTokenizer.from_pretrained(checkpoint),
+    image_processor=CLIPImageProcessor.from_pretrained(checkpoint)
+)
+
+model.to('cuda')
+
+
+prompt = processor.tokenizer.apply_chat_template(
+    [{'role': 'user', 'content': "What's the content of the image?<image>"}],
+    tokenize=False,
+    add_generation_prompt=True
+)
+url = "https://www.ilankelman.org/stopsigns/australia.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+inputs = processor(text=prompt, images=image, return_tensors="pt")
+inputs = {k: v.to('cuda') for k, v in inputs.items()}
+      
+# Generate
+generate_ids = model.generate(**inputs, max_length=30)
+output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+print(output)