model upload

config.json

@@ -0,0 +1,110 @@
+{
+  "_commit_hash": "58597eee6783b5d4405df333573fe4b4368bce29",
+  "architectures": [
+    "GitForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_git.GitConfig",
+    "AutoModelForCausalLM": "modeling_git.GitForCausalLM"
+  },
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 101,
+  "classifier_dropout": null,
+  "eos_token_id": 102,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "git",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_image_with_embedding": null,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_cache": true,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "git_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vocab_size": 32778
+}

configuration_git.py

@@ -0,0 +1,164 @@
+# coding=utf-8
+# Copyright 2022 The HuggingFace Inc. team. All rights reserved.
+#
+# 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.
+
+import os
+from typing import Union
+
+from transformers.configuration_utils import PretrainedConfig
+import transformers.models.git.configuration_git as configuration_git
+
+
+GIT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "microsoft/git-base": "https://huggingface.co/microsoft/git-base/resolve/main/config.json",
+}
+
+
+class GitVisionConfig(configuration_git.GitVisionConfig, dict):
+    def __init__(self, *args, **kwargs):
+        configuration_git.GitVisionConfig.__init__(
+                self, *args, **kwargs)
+        dict.__init__(self, **self.__dict__)
+
+    def toJSON(self):
+        return json.dumps(
+            self,
+            default=lambda o: o.__dict__, 
+            sort_keys=True,
+            indent=4)
+
+
+class GitConfig(PretrainedConfig, dict):
+    r"""
+    This is the configuration class to store the configuration of a [`GitModel`]. It is used to instantiate a GIT model
+    according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the GIT
+    [microsoft/git-base](https://huggingface.co/microsoft/git-base) architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        vision_config (`dict`, *optional*):
+            Dictionary of configuration options used to initialize [`GitVisionConfig`].
+        vocab_size (`int`, *optional*, defaults to 30522):
+            Vocabulary size of the GIT model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`GitModel`].
+        hidden_size (`int`, *optional*, defaults to 768):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_hidden_layers (`int`, *optional*, defaults to 6):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 12):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (`int`, *optional*, defaults to 3072):
+            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
+        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"silu"` and `"gelu_new"` are supported.
+        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
+            The dropout ratio for the attention probabilities.
+        max_position_embeddings (`int`, *optional*, defaults to 1024):
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
+            The epsilon used by the layer normalization layers.
+        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
+            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
+            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
+            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
+            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
+            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models).
+        num_image_with_embedding (`int`, *optional*):
+            The number of temporal embeddings to add, in case the model is used for video captioning/VQA.
+
+    Examples:
+
+    ```python
+    >>> from transformers import GitConfig, GitModel
+
+    >>> # Initializing a GIT microsoft/git-base style configuration
+    >>> configuration = GitConfig()
+
+    >>> # Initializing a model (with random weights) from the microsoft/git-base style configuration
+    >>> model = GitModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "git"
+
+    def __init__(
+        self,
+        vision_config=None,
+        vocab_size=32778,
+        hidden_size=768,
+        num_hidden_layers=6,
+        num_attention_heads=12,
+        intermediate_size=3072,
+        hidden_act="gelu",
+        hidden_dropout_prob=0.1,
+        attention_probs_dropout_prob=0.1,
+        max_position_embeddings=1024,
+        initializer_range=0.02,
+        layer_norm_eps=1e-12,
+        pad_token_id=0,
+        position_embedding_type="absolute",
+        use_cache=True,
+        tie_word_embeddings=True,
+        bos_token_id=101,
+        eos_token_id=102,
+        num_image_with_embedding=None,
+        **kwargs,
+    ):
+        PretrainedConfig.__init__(
+                self,
+                bos_token_id=bos_token_id, eos_token_id=eos_token_id, pad_token_id=pad_token_id, **kwargs)
+
+        if vision_config is None:
+            vision_config = {}
+        self.vision_config = GitVisionConfig(**vision_config)
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.hidden_act = hidden_act
+        self.intermediate_size = intermediate_size
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.initializer_range = initializer_range
+        self.layer_norm_eps = layer_norm_eps
+        self.position_embedding_type = position_embedding_type
+        self.use_cache = use_cache
+        self.tie_word_embeddings = tie_word_embeddings
+        self.num_image_with_embedding = num_image_with_embedding
+
+        self.bos_token_id = bos_token_id
+        self.eos_token_id = eos_token_id
+
+        dict.__init__(self, **self.__dict__)
+
+    def toJSON(self):
+        return json.dumps(
+            self,
+            default=lambda o: o.__dict__, 
+            sort_keys=True,
+            indent=4)

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "eos_token_id": 102,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0"
+}

modeling_git.py

@@ -0,0 +1,100 @@
+import transformers
+from transformers import AutoProcessor, AutoModelForCausalLM
+from transformers import ViTFeatureExtractor, ViTModel, ViTConfig
+from typing import List, Optional, Tuple, Union
+import warnings
+import ipdb
+import os
+import torch
+from torch import nn
+from torch.nn import CrossEntropyLoss
+from itertools import product
+import numpy as np
+import transformers.models.git.modeling_git as modeling_git
+import transformers.models.vit.modeling_vit as modeling_vit
+from transformers.models.opt.modeling_opt import OPTConfig
+import transformers.models.opt.modeling_opt as hg_opt
+import transformers.models.clip.modeling_clip as modeling_clip
+
+
+class GitForCausalLM(modeling_git.GitForCausalLM):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        del self.output
+        self.output = nn.Linear(
+                self.config.hidden_size,
+                self.config.vocab_size,
+                bias=False)
+        self.post_init()
+
+        del self.git.image_encoder
+        self.git.image_encoder = ViTModel.from_pretrained('facebook/dino-vitb16')
+        dino_cfg = self.git.image_encoder.config
+        config = self.git.config
+        config.vision_config.hidden_size = dino_cfg.hidden_size
+
+        del self.git.visual_projection
+        self.git.visual_projection = modeling_git.GitProjection(config)
+        num_tks = (dino_cfg.image_size // dino_cfg.patch_size) ** 2 + 1
+        self.git.encoder.layer[0].attention.self.image_patch_tokens = num_tks
+    
+    def forward(
+        self,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        pixel_values: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        past_key_values: Optional[List[torch.Tensor]] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple[torch.Tensor], modeling_git.CausalLMOutputWithPast]:
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        if labels is not None:
+            use_cache = False
+
+        outputs = self.git(
+            input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            pixel_values=pixel_values,
+            head_mask=head_mask,
+            inputs_embeds=inputs_embeds,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+
+        sequence_output = outputs[0]
+        logits = self.output(sequence_output)
+
+        loss = None
+        if labels is not None:
+            # we are doing next-token prediction; shift prediction scores and input ids by one
+            if pixel_values is not None:
+                num_image_tokens = self.git.encoder.layer[0].attention.self.image_patch_tokens
+            else:
+                num_image_tokens = 0
+            shifted_logits = logits[:, num_image_tokens:-1, :].contiguous()
+            labels = labels[:, 1:].contiguous()
+            loss_fct = CrossEntropyLoss()
+            loss = loss_fct(shifted_logits.view(-1, self.config.vocab_size), labels.view(-1))
+
+        if not return_dict:
+            output = (logits,) + outputs[1:]
+            return ((loss,) + output) if loss is not None else output
+
+        return modeling_git.CausalLMOutputWithPast(
+            loss=loss,
+            logits=logits,
+            past_key_values=outputs.past_key_values,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e0e3312c8f6380c48894eec9d4f20ad0ae4b27167695bab3395e38e269df2f
+size 792134047

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "additional_special_tokens": [
+    "<image>",
+    "<PERSON>"
+  ],
+  "pad_token": "<pad>"
+}

tokenizer_config.json

@@ -0,0 +1,5 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}