Delete visual_gen

visual_gen/PixWizard/README.md

@@ -1,22 +0,0 @@
----
-license: apache-2.0
-language:
-- en
----
-
-# PixWizard Model Card
-
-## Paper or resources for more information:
-Paper: [https://arxiv.org/abs/2409.15278](https://arxiv.org/abs/2409.15278) \
-Code: [https://github.com/AFeng-x/PixWizard](https://github.com/AFeng-x/PixWizard)
-
-
-## Citations
-```
-@article{lin2024pixwizard,
-  title={PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions},
-  author={Lin, Weifeng and Wei, Xinyu and Zhang, Renrui and Zhuo, Le and Zhao, Shitian and Huang, Siyuan and Xie, Junlin and Qiao, Yu and Gao, Peng and Li, Hongsheng},
-  journal={arXiv preprint arXiv:2409.15278},
-  year={2024}
-}
-```

visual_gen/PixWizard/consolidated.00-of-01.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:927ec489b43235cdbeda6cb8fac5b1db26e3b0c76eb0011d04f3a9af0170994b
-size 8046201485

visual_gen/PixWizard/consolidated_ema.00-of-01.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85716aac6fe46893a55a80e1f6b152b94094c35f79fad240bab81f0829f9b163
-size 8046205577

visual_gen/PixWizard/gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

visual_gen/PixWizard/model_args.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5e07e0ff9a089bc12e827ff20c4653fd17596c301ae144c3d0110d34274f4da2
-size 2284

visual_gen/clip-vit-large-patch14-336/config.json

@@ -1,179 +0,0 @@
-{
-  "_name_or_path": "openai/clip-vit-large-patch14-336",
-  "architectures": [
-    "CLIPModel"
-  ],
-  "initializer_factor": 1.0,
-  "logit_scale_init_value": 2.6592,
-  "model_type": "clip",
-  "projection_dim": 768,
-  "text_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "bos_token_id": 0,
-    "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": 2,
-    "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"
-    },
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "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,
-    "max_position_embeddings": 77,
-    "min_length": 0,
-    "model_type": "clip_text_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 1,
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 768,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": 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": "4.21.3",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "vocab_size": 49408
-  },
-  "text_config_dict": {
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12,
-    "projection_dim": 768
-  },
-  "torch_dtype": "float32",
-  "transformers_version": null,
-  "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": 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": 1024,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 336,
-    "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": "clip_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": 768,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": 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": "4.21.3",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "vision_config_dict": {
-    "hidden_size": 1024,
-    "image_size": 336,
-    "intermediate_size": 4096,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14,
-    "projection_dim": 768
-  }
-}

visual_gen/clip-vit-large-patch14-336/preprocessor_config.json

@@ -1,19 +0,0 @@
-{
-  "crop_size": 336,
-  "do_center_crop": true,
-  "do_normalize": true,
-  "do_resize": true,
-  "feature_extractor_type": "CLIPFeatureExtractor",
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "resample": 3,
-  "size": 336
-}

visual_gen/clip-vit-large-patch14-336/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6032c2e0caae3dc2d4fba35535fa6307dbb49df59c7e182b1bc4b3329b81801
-size 1711974081

visual_gen/clip-vit-large-patch14-336/special_tokens_map.json

@@ -1 +0,0 @@
-{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

visual_gen/clip-vit-large-patch14-336/tf_model.h5

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d12828ca8f0f3c92194f277b7d893da7f2fb7824d0b99dedb305eb48eb46bb7f
-size 1712454232

visual_gen/clip-vit-large-patch14-336/tokenizer_config.json

@@ -1 +0,0 @@
-{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "do_lower_case": true, "name_or_path": "openai/clip-vit-base-patch32", "model_max_length": 77, "special_tokens_map_file": "/home/suraj/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5", "tokenizer_class": "CLIPTokenizer"}

visual_gen/gemma-2b/README.md

@@ -1,455 +0,0 @@
----
-library_name: transformers
-new_version: google/gemma-2-2b
-license: gemma
-extra_gated_heading: Access Gemma on Hugging Face
-extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
-  agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
-  Face and click below. Requests are processed immediately.
-extra_gated_button_content: Acknowledge license
----
-
-# Gemma Model Card
-
-**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
-
-This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it). 
-
-**Resources and Technical Documentation**:
-
-* [Gemma Technical Report](https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf)
-* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
-* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
-* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-2b-gg-hf)
-
-**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2b)
-
-**Authors**: Google
-
-## Model Information
-
-Summary description and brief definition of inputs and outputs.
-
-### Description
-
-Gemma is a family of lightweight, state-of-the-art open models from Google,
-built from the same research and technology used to create the Gemini models.
-They are text-to-text, decoder-only large language models, available in English,
-with open weights, pre-trained variants, and instruction-tuned variants. Gemma
-models are well-suited for a variety of text generation tasks, including
-question answering, summarization, and reasoning. Their relatively small size
-makes it possible to deploy them in environments with limited resources such as
-a laptop, desktop or your own cloud infrastructure, democratizing access to
-state of the art AI models and helping foster innovation for everyone. 
-
-### Context Length
-Models are trained on a context length of 8192 tokens.
-
-### Usage
-
-Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.
-
-
-#### Fine-tuning the model
-
-You can find fine-tuning scripts and notebook under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples) of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) repository. To adapt it to this model, simply change the model-id to `google/gemma-2b`.
-In that repository, we provide:
-
-* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA
-* A script to perform SFT using FSDP on TPU devices
-* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset
-
-
-
-#### Running the model on a CPU
-
-
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
-
-input_text = "Write me a poem about Machine Learning."
-input_ids = tokenizer(input_text, return_tensors="pt")
-
-outputs = model.generate(**input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-
-
-#### Running the model on a single / multi GPU
-
-
-```python
-# pip install accelerate
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto")
-
-input_text = "Write me a poem about Machine Learning."
-input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
-
-outputs = model.generate(**input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-
-
-#### Running the model on a GPU using different precisions
-
-* _Using `torch.float16`_
-
-```python
-# pip install accelerate
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", revision="float16")
-
-input_text = "Write me a poem about Machine Learning."
-input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
-
-outputs = model.generate(**input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-
-* _Using `torch.bfloat16`_
-
-```python
-# pip install accelerate
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.bfloat16)
-
-input_text = "Write me a poem about Machine Learning."
-input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
-
-outputs = model.generate(**input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-
-#### Quantized Versions through `bitsandbytes`
-
-* _Using 8-bit precision (int8)_
-
-```python
-# pip install bitsandbytes accelerate
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
-
-quantization_config = BitsAndBytesConfig(load_in_8bit=True)
-
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
-
-input_text = "Write me a poem about Machine Learning."
-input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
-
-outputs = model.generate(**input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-
-* _Using 4-bit precision_
-
-```python
-# pip install bitsandbytes accelerate
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
-
-quantization_config = BitsAndBytesConfig(load_in_4bit=True)
-
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
-
-input_text = "Write me a poem about Machine Learning."
-input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
-
-outputs = model.generate(**input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-
-
-#### Other optimizations
-
-* _Flash Attention 2_
-
-First make sure to install `flash-attn` in your environment `pip install flash-attn`
-
-```diff
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, 
-    torch_dtype=torch.float16, 
-+   attn_implementation="flash_attention_2"
-).to(0)
-```
-
-### Inputs and outputs
-
-*   **Input:** Text string, such as a question, a prompt, or a document to be
-    summarized.
-*   **Output:** Generated English-language text in response to the input, such
-    as an answer to a question, or a summary of a document.
-
-## Model Data
-
-Data used for model training and how the data was processed.
-
-### Training Dataset
-
-These models were trained on a dataset of text data that includes a wide variety
-of sources, totaling 6 trillion tokens. Here are the key components:
-
-* Web Documents: A diverse collection of web text ensures the model is exposed
-  to a broad range of linguistic styles, topics, and vocabulary. Primarily
-  English-language content.
-* Code: Exposing the model to code helps it to learn the syntax and patterns of
-  programming languages, which improves its ability to generate code or
-  understand code-related questions.
-* Mathematics: Training on mathematical text helps the model learn logical
-  reasoning, symbolic representation, and to address mathematical queries.
-
-The combination of these diverse data sources is crucial for training a powerful
-language model that can handle a wide variety of different tasks and text
-formats.
-
-### Data Preprocessing
-
-Here are the key data cleaning and filtering methods applied to the training
-data:
-
-* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
-  applied at multiple stages in the data preparation process to ensure the
-  exclusion of harmful and illegal content
-* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
-  reliable, automated techniques were used to filter out certain personal
-  information and other sensitive data from training sets.
-* Additional methods: Filtering based on content quality and safely in line with
-  [our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
-
-## Implementation Information
-
-Details about the model internals.
-
-### Hardware
-
-Gemma was trained using the latest generation of
-[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
-
-Training large language models requires significant computational power. TPUs,
-designed specifically for matrix operations common in machine learning, offer
-several advantages in this domain:
-
-* Performance: TPUs are specifically designed to handle the massive computations
-  involved in training LLMs. They can speed up training considerably compared to
-  CPUs.
-* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
-  for the handling of large models and batch sizes during training. This can
-  lead to better model quality.
-* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
-  handling the growing complexity of large foundation models. You can distribute
-  training across multiple TPU devices for faster and more efficient processing.
-* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
-  solution for training large models compared to CPU-based infrastructure,
-  especially when considering the time and resources saved due to faster
-  training.
-* These advantages are aligned with
-  [Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
-
-### Software
-
-Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ml-pathways).
-
-JAX allows researchers to take advantage of the latest generation of hardware,
-including TPUs, for faster and more efficient training of large models.
-
-ML Pathways is Google's latest effort to build artificially intelligent systems
-capable of generalizing across multiple tasks. This is specially suitable for
-[foundation models](https://ai.google/discover/foundation-models/), including large language models like
-these ones.
-
-Together, JAX and ML Pathways are used as described in the
-[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
-controller' programming model of Jax and Pathways allows a single Python
-process to orchestrate the entire training run, dramatically simplifying the
-development workflow."
-
-## Evaluation
-
-Model evaluation metrics and results.
-
-### Benchmark Results
-
-These models were evaluated against a large collection of different datasets and
-metrics to cover different aspects of text generation:
-
-| Benchmark                      | Metric        | 2B Params | 7B Params |
-| ------------------------------ | ------------- | ----------- | --------- |
-| [MMLU](https://arxiv.org/abs/2009.03300)                   | 5-shot, top-1 | 42.3        | 64.3      |
-| [HellaSwag](https://arxiv.org/abs/1905.07830)         | 0-shot        |71.4        | 81.2      |
-| [PIQA](https://arxiv.org/abs/1911.11641)                   | 0-shot        | 77.3        | 81.2      |
-| [SocialIQA](https://arxiv.org/abs/1904.09728)      | 0-shot        | 49.7        | 51.8      |
-| [BooIQ](https://arxiv.org/abs/1905.10044)                | 0-shot        | 69.4        | 83.2      |
-| [WinoGrande](https://arxiv.org/abs/1907.10641)       | partial score | 65.4        | 72.3      |
-| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot        | 65.3        | 71.3      |
-| [OpenBookQA](https://arxiv.org/abs/1809.02789)       |               | 47.8        | 52.8      |
-| [ARC-e](https://arxiv.org/abs/1911.01547)                  |               | 73.2        | 81.5      |
-| [ARC-c](https://arxiv.org/abs/1911.01547)                   |               | 42.1        | 53.2      |
-| [TriviaQA](https://arxiv.org/abs/1705.03551)           | 5-shot        | 53.2        | 63.4      |
-| [Natural Questions](https://github.com/google-research-datasets/natural-questions)  | 5-shot        | 12.5       | 23        |
-| [HumanEval](https://arxiv.org/abs/2107.03374)      | pass@1        | 22.0        | 32.3      |
-| [MBPP](https://arxiv.org/abs/2108.07732)                   | 3-shot        | 29.2        | 44.4      |
-| [GSM8K](https://arxiv.org/abs/2110.14168)                | maj@1         | 17.7        | 46.4      |
-| [MATH](https://arxiv.org/abs/2108.07732)                   | 4-shot        | 11.8          | 24.3      |
-| [AGIEval](https://arxiv.org/abs/2304.06364)           |               | 24.2        | 41.7      |
-| [BIG-Bench](https://arxiv.org/abs/2206.04615)         |               | 35.2        | 55.1      |
-| ------------------------------ | ------------- | ----------- | --------- |
-| **Average**                    |               | **45.0**    | **56.9**  |
-
-## Ethics and Safety
-
-Ethics and safety evaluation approach and results.
-
-### Evaluation Approach
-
-Our evaluation methods include structured evaluations and internal red-teaming
-testing of relevant content policies. Red-teaming was conducted by a number of
-different teams, each with different goals and human evaluation metrics. These
-models were evaluated against a number of different categories relevant to
-ethics and safety, including:
-
-* Text-to-Text Content Safety: Human evaluation on prompts covering safety
-  policies including child sexual abuse and exploitation, harassment, violence
-  and gore, and hate speech.
-* Text-to-Text Representational Harms: Benchmark against relevant academic
-  datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
-* Memorization: Automated evaluation of memorization of training data, including
-  the risk of personally identifiable information exposure.
-* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
-  biological, radiological, and nuclear (CBRN) risks.
-
-### Evaluation Results
-
-The results of ethics and safety evaluations are within acceptable thresholds
-for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child
-safety, content safety, representational harms, memorization, large-scale harms.
-On top of robust internal evaluations, the results of well known safety
-benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
-are shown here.
-
-**Update**: These numbers reflect the new numbers from the updated v1.1 IT models. For the original v1 numbers, please consult the technical report's appendix for the results.
-
-| Benchmark                      | Metric        | Gemma v1.1 IT 2B   | Gemma v1.1 IT 7B    |
-| ------------------------------ | ------------- | ----------- | --------- |
-| [RealToxicity](https://arxiv.org/abs/2009.11462)        | average       | 6.86        | 7.90      |
-| [BOLD](https://arxiv.org/abs/2101.11718)                   |               | 45.57       | 49.08     |
-| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/)        | top-1         | 45.82       | 51.33     |
-| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2)               | 1-shot, top-1 | 62.58       | 92.54     |
-| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2)            | top-1         | 54.62       | 71.99     |
-| [Winogender](https://arxiv.org/abs/1804.09301)       | top-1         | 51.25       | 54.17     |
-| [TruthfulQA](https://arxiv.org/abs/2109.07958)       |               | 31.81       | 44.84     |
-| [Winobias 1_2](https://arxiv.org/abs/1804.06876)       |               | 56.12       | 59.09     |
-| [Winobias 2_2](https://arxiv.org/abs/1804.06876)       |               | 91.10       | 92.23     |
-| [Toxigen](https://arxiv.org/abs/2203.09509)             |               | 29.77       | 39.59     |
-| ------------------------------ | ------------- | ----------- | --------- |
-
-
-## Usage and Limitations
-
-These models have certain limitations that users should be aware of.
-
-### Intended Usage
-
-Open Large Language Models (LLMs) have a wide range of applications across
-various industries and domains. The following list of potential uses is not
-comprehensive. The purpose of this list is to provide contextual information
-about the possible use-cases that the model creators considered as part of model
-training and development.
-
-* Content Creation and Communication
-  * Text Generation: These models can be used to generate creative text formats
-    such as poems, scripts, code, marketing copy, and email drafts.
-  * Chatbots and Conversational AI: Power conversational interfaces for customer
-    service, virtual assistants, or interactive applications.
-  * Text Summarization: Generate concise summaries of a text corpus, research
-    papers, or reports.
-* Research and Education
-  * Natural Language Processing (NLP) Research: These models can serve as a
-    foundation for researchers to experiment with NLP techniques, develop
-    algorithms, and contribute to the advancement of the field.
-  * Language Learning Tools: Support interactive language learning experiences,
-    aiding in grammar correction or providing writing practice.
-  * Knowledge Exploration: Assist researchers in exploring large bodies of text
-    by generating summaries or answering questions about specific topics.
-
-### Limitations
-
-* Training Data
-  * The quality and diversity of the training data significantly influence the
-    model's capabilities. Biases or gaps in the training data can lead to
-    limitations in the model's responses.
-  * The scope of the training dataset determines the subject areas the model can
-    handle effectively.
-* Context and Task Complexity
-  * LLMs are better at tasks that can be framed with clear prompts and
-    instructions. Open-ended or highly complex tasks might be challenging.
-  * A model's performance can be influenced by the amount of context provided
-    (longer context generally leads to better outputs, up to a certain point).
-* Language Ambiguity and Nuance
-  * Natural language is inherently complex. LLMs might struggle to grasp subtle
-    nuances, sarcasm, or figurative language.
-* Factual Accuracy
-  * LLMs generate responses based on information they learned from their
-    training datasets, but they are not knowledge bases. They may generate
-    incorrect or outdated factual statements.
-* Common Sense
-  * LLMs rely on statistical patterns in language. They might lack the ability
-    to apply common sense reasoning in certain situations.
-
-### Ethical Considerations and Risks
-
-The development of large language models (LLMs) raises several ethical concerns.
-In creating an open model, we have carefully considered the following:
-
-* Bias and Fairness
-  * LLMs trained on large-scale, real-world text data can reflect socio-cultural
-    biases embedded in the training material. These models underwent careful
-    scrutiny, input data pre-processing described and posterior evaluations
-    reported in this card.
-* Misinformation and Misuse
-  * LLMs can be misused to generate text that is false, misleading, or harmful.
-  * Guidelines are provided for responsible use with the model, see the
-    [Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible).
-* Transparency and Accountability:
-  * This model card summarizes details on the models' architecture,
-    capabilities, limitations, and evaluation processes.
-  * A responsibly developed open model offers the opportunity to share
-    innovation by making LLM technology accessible to developers and researchers
-    across the AI ecosystem.
-
-Risks identified and mitigations:
-
-* Perpetuation of biases: It's encouraged to perform continuous monitoring
-  (using evaluation metrics, human review) and the exploration of de-biasing
-  techniques during model training, fine-tuning, and other use cases.
-* Generation of harmful content: Mechanisms and guidelines for content safety
-  are essential. Developers are encouraged to exercise caution and implement
-  appropriate content safety safeguards based on their specific product policies
-  and application use cases.
-* Misuse for malicious purposes: Technical limitations and developer and
-  end-user education can help mitigate against malicious applications of LLMs.
-  Educational resources and reporting mechanisms for users to flag misuse are
-  provided. Prohibited uses of Gemma models are outlined in the
-  [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
-* Privacy violations: Models were trained on data filtered for removal of PII
-  (Personally Identifiable Information). Developers are encouraged to adhere to
-  privacy regulations with privacy-preserving techniques.
-
-### Benefits
-
-At the time of release, this family of models provides high-performance open
-large language model implementations designed from the ground up for Responsible
-AI development compared to similarly sized models.
-
-Using the benchmark evaluation metrics described in this document, these models
-have shown to provide superior performance to other, comparably-sized open model
-alternatives.

visual_gen/gemma-2b/config.json

@@ -1,27 +0,0 @@
-{
-  "architectures": [
-    "GemmaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "head_dim": 256,
-  "hidden_act": "gelu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 16384,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 18,
-  "num_key_value_heads": 1,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.0.dev0",
-  "use_cache": true,
-  "vocab_size": 256000
-}

visual_gen/gemma-2b/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.38.0.dev0"
-}

visual_gen/gemma-2b/gitattributes

@@ -1,37 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-tokenizer.json filter=lfs diff=lfs merge=lfs -text
-gemma-2b.gguf filter=lfs diff=lfs merge=lfs -text

visual_gen/gemma-2b/model-00001-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:98caad07f1e1d17fede7734906d6881d4cb231e1d0cd2ebcf7fc8a6317eee4d6
-size 4945242264

visual_gen/gemma-2b/model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3342a2f7db857bc9873c699eef1416eb2b320603e5e042a6f7736689b26382cb
-size 67121608

visual_gen/gemma-2b/model.safetensors.index.json

@@ -1,171 +0,0 @@
-{
-  "metadata": {
-    "total_size": 5012344832
-  },
-  "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors"
-  }
-}

visual_gen/gemma-2b/special_tokens_map.json

@@ -1,34 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
-  "bos_token": {
-    "content": "<bos>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<eos>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

visual_gen/gemma-2b/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c15eb04bc5ad609fb26533e8525302c5640a945e5f67f65b7c849900acda7d99
-size 17518497

visual_gen/gemma-2b/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
-size 4241003

visual_gen/gemma-2b/tokenizer_config.json

@@ -1,1516 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<eos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<bos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<mask>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "5": {
-      "content": "<2mass>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "6": {
-      "content": "[@BOS@]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "7": {
-      "content": "<unused0>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "8": {
-      "content": "<unused1>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "9": {
-      "content": "<unused2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "10": {
-      "content": "<unused3>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "11": {
-      "content": "<unused4>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "12": {
-      "content": "<unused5>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "13": {
-      "content": "<unused6>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "14": {
-      "content": "<unused7>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "15": {
-      "content": "<unused8>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "16": {
-      "content": "<unused9>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "17": {
-      "content": "<unused10>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "18": {
-      "content": "<unused11>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "19": {
-      "content": "<unused12>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "20": {
-      "content": "<unused13>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "21": {
-      "content": "<unused14>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "22": {
-      "content": "<unused15>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "23": {
-      "content": "<unused16>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "24": {
-      "content": "<unused17>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "25": {
-      "content": "<unused18>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "26": {
-      "content": "<unused19>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "27": {
-      "content": "<unused20>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "28": {
-      "content": "<unused21>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "29": {
-      "content": "<unused22>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "30": {
-      "content": "<unused23>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "31": {
-      "content": "<unused24>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "32": {
-      "content": "<unused25>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "33": {
-      "content": "<unused26>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "34": {
-      "content": "<unused27>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "35": {
-      "content": "<unused28>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "36": {
-      "content": "<unused29>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "37": {
-      "content": "<unused30>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "38": {
-      "content": "<unused31>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "39": {
-      "content": "<unused32>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "40": {
-      "content": "<unused33>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "41": {
-      "content": "<unused34>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "42": {
-      "content": "<unused35>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "43": {
-      "content": "<unused36>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "44": {
-      "content": "<unused37>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "45": {
-      "content": "<unused38>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "46": {
-      "content": "<unused39>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "47": {
-      "content": "<unused40>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "48": {
-      "content": "<unused41>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "49": {
-      "content": "<unused42>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50": {
-      "content": "<unused43>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "51": {
-      "content": "<unused44>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "52": {
-      "content": "<unused45>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "53": {
-      "content": "<unused46>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "54": {
-      "content": "<unused47>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "55": {
-      "content": "<unused48>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "56": {
-      "content": "<unused49>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57": {
-      "content": "<unused50>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "58": {
-      "content": "<unused51>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "59": {
-      "content": "<unused52>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "60": {
-      "content": "<unused53>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "61": {
-      "content": "<unused54>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "62": {
-      "content": "<unused55>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "63": {
-      "content": "<unused56>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "64": {
-      "content": "<unused57>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "65": {
-      "content": "<unused58>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "66": {
-      "content": "<unused59>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "67": {
-      "content": "<unused60>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "68": {
-      "content": "<unused61>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "69": {
-      "content": "<unused62>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "70": {
-      "content": "<unused63>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "71": {
-      "content": "<unused64>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "72": {
-      "content": "<unused65>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "73": {
-      "content": "<unused66>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "74": {
-      "content": "<unused67>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "75": {
-      "content": "<unused68>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "76": {
-      "content": "<unused69>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "77": {
-      "content": "<unused70>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "78": {
-      "content": "<unused71>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "79": {
-      "content": "<unused72>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "80": {
-      "content": "<unused73>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "81": {
-      "content": "<unused74>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "82": {
-      "content": "<unused75>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "83": {
-      "content": "<unused76>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "84": {
-      "content": "<unused77>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "85": {
-      "content": "<unused78>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "86": {
-      "content": "<unused79>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "87": {
-      "content": "<unused80>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "88": {
-      "content": "<unused81>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "89": {
-      "content": "<unused82>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "90": {
-      "content": "<unused83>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "91": {
-      "content": "<unused84>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92": {
-      "content": "<unused85>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "93": {
-      "content": "<unused86>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "94": {
-      "content": "<unused87>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "95": {
-      "content": "<unused88>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "96": {
-      "content": "<unused89>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "97": {
-      "content": "<unused90>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "98": {
-      "content": "<unused91>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "99": {
-      "content": "<unused92>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "100": {
-      "content": "<unused93>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "101": {
-      "content": "<unused94>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "102": {
-      "content": "<unused95>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "103": {
-      "content": "<unused96>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "104": {
-      "content": "<unused97>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "105": {
-      "content": "<unused98>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "106": {
-      "content": "<start_of_turn>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "107": {
-      "content": "<end_of_turn>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "108": {
-      "content": "\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "109": {
-      "content": "\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "110": {
-      "content": "\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "111": {
-      "content": "\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "112": {
-      "content": "\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "113": {
-      "content": "\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "114": {
-      "content": "\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "115": {
-      "content": "\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "116": {
-      "content": "\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "117": {
-      "content": "\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "118": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "119": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "120": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "121": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "122": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "123": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "124": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "125": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "126": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "127": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "128": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "129": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "130": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "131": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "132": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "133": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "134": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "135": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "136": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "137": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "138": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "169": {
-      "content": "<table>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "170": {
-      "content": "<caption>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "171": {
-      "content": "<thead>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "172": {
-      "content": "<tbody>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "173": {
-      "content": "<tfoot>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "174": {
-      "content": "<tr>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "175": {
-      "content": "<th>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "176": {
-      "content": "<td>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "177": {
-      "content": "</table>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "178": {
-      "content": "</caption>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "179": {
-      "content": "</thead>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "180": {
-      "content": "</tbody>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "181": {
-      "content": "</tfoot>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "182": {
-      "content": "</tr>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "183": {
-      "content": "</th>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "184": {
-      "content": "</td>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "185": {
-      "content": "<h1>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "186": {
-      "content": "<h2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "187": {
-      "content": "<h3>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "188": {
-      "content": "<h4>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "189": {
-      "content": "<h5>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "190": {
-      "content": "<h6>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "191": {
-      "content": "<blockquote>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "192": {
-      "content": "</h1>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "193": {
-      "content": "</h2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "194": {
-      "content": "</h3>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "195": {
-      "content": "</h4>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "196": {
-      "content": "</h5>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "197": {
-      "content": "</h6>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "198": {
-      "content": "</blockquote>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "199": {
-      "content": "<strong>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "200": {
-      "content": "<em>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "201": {
-      "content": "<b>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "202": {
-      "content": "<i>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "203": {
-      "content": "<u>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "204": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "205": {
-      "content": "<sub>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "206": {
-      "content": "<sup>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "207": {
-      "content": "<code>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "208": {
-      "content": "</strong>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "209": {
-      "content": "</em>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "210": {
-      "content": "</b>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "211": {
-      "content": "</i>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "212": {
-      "content": "</u>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "213": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "214": {
-      "content": "</sub>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "215": {
-      "content": "</sup>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "216": {
-      "content": "</code>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
-  "bos_token": "<bos>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<eos>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}

visual_gen/sdxl-vae/README.md

@@ -1,39 +0,0 @@
----
-license: mit
-tags:
-- stable-diffusion
-- stable-diffusion-diffusers
-inference: false
----
-# SDXL - VAE
-
-#### How to use with 🧨 diffusers
-You can integrate this fine-tuned VAE decoder to your existing `diffusers` workflows, by including a `vae` argument to the `StableDiffusionPipeline`
-```py
-from diffusers.models import AutoencoderKL
-from diffusers import StableDiffusionPipeline
-
-model = "stabilityai/your-stable-diffusion-model"
-vae = AutoencoderKL.from_pretrained("stabilityai/sdxl-vae")
-pipe = StableDiffusionPipeline.from_pretrained(model, vae=vae)
-```
-
-## Model 
-[SDXL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9) is a [latent diffusion model](https://arxiv.org/abs/2112.10752), where the diffusion operates in a pretrained, 
-learned (and fixed) latent space of an autoencoder. 
-While the bulk of the semantic composition is done by the latent diffusion model, 
-we can improve _local_, high-frequency details in generated images by improving the quality of the autoencoder. 
-To this end, we train the same autoencoder architecture used for the original [Stable Diffusion](https://github.com/CompVis/stable-diffusion) at a larger batch-size (256 vs 9) 
-and additionally track the weights with an exponential moving average (EMA). 
-The resulting autoencoder outperforms the original model in all evaluated reconstruction metrics, see the table below.
-
-
-## Evaluation 
-_SDXL-VAE vs original kl-f8 VAE vs f8-ft-MSE_
-### COCO 2017 (256x256, val, 5000 images)
-| Model    | rFID | PSNR         | SSIM          | PSIM          | Link                                                                                                 | Comments                                                                                        
-|----------|------|--------------|---------------|---------------|------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
-|          |      |              |               |               |                                                                                                      |                                                                                                 |
-| SDXL-VAE | 4.42 | 24.7 +/- 3.9 | 0.73 +/- 0.13 | 0.88 +/- 0.27 | https://huggingface.co/stabilityai/sdxl-vae/blob/main/sdxl_vae.safetensors                                                                                                     | as used in SDXL                                                                                 |
-| original | 4.99 | 23.4 +/- 3.8 | 0.69 +/- 0.14 | 1.01 +/- 0.28 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip                                               | as used in SD                                                                                   |
-| ft-MSE   | 4.70 | 24.5 +/- 3.7 | 0.71 +/- 0.13 | 0.92 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |

visual_gen/sdxl-vae/config.json

@@ -1,31 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.18.0.dev0",
-  "_name_or_path": ".",
-  "act_fn": "silu",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "in_channels": 3,
-  "latent_channels": 4,
-  "layers_per_block": 2,
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 1024,
-  "scaling_factor": 0.13025,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
-}

visual_gen/sdxl-vae/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341
-size 334643268

visual_gen/sdxl-vae/gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text