Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,46 @@
+*.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
+onnx/audio_encoder.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_quantized.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_uint8.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,738 @@
+---
+license: gemma
+library_name: transformers.js
+pipeline_tag: image-text-to-text
+base_model: google/gemma-3n-E2B-it
+tags:
+- automatic-speech-recognition
+- automatic-speech-translation
+- audio-text-to-text
+- video-text-to-text
+---
+
+> [!Note]
+> This repository corresponds to the launch version of Gemma 3n E2B IT (Instruct), to be used with Hugging Face `transformers.js`,
+> supporting text, audio, and vision (image and video) inputs.
+> 
+> Gemma 3n models have multiple architecture innovations:
+>  * They are available in two sizes based on [effective parameters](https://ai.google.dev/gemma/docs/gemma-3n#parameters). While the raw parameter count of this model is 6B, the architecture design allows the model to be run with a memory footprint comparable to a traditional 2B model by offloading low-utilization matrices from the accelerator.
+>  * They use a MatFormer architecture that allows nesting sub-models within the [E4B model](https://huggingface.co/google/gemma-3n-E4B-it). We provide one sub-model (this model repository), or you can access a spectrum of custom-sized models using the [Mix-and-Match method](https://goo.gle/gemma3n-matformer-lab).
+>
+> Learn more about these techniques in the [technical blog post](https://developers.googleblog.com/en/introducing-gemma-3n-developer-guide)
+> and the [Gemma documentation](https://ai.google.dev/gemma/docs/gemma-3n). 
+
+
+
+# Gemma 3n model card
+
+**Model Page**: [Gemma 3n](https://ai.google.dev/gemma/docs/gemma-3n)
+
+**Resources and Technical Documentation**:
+
+-   [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
+-   [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma-3n)
+-   [Gemma on HuggingFace](https://huggingface.co/collections/google/gemma-3n-685065323f5984ef315c93f4)
+-   [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemma3n)
+
+**Terms of Use**: [Terms](https://ai.google.dev/gemma/terms)\
+**Authors**: Google DeepMind
+
+## 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.
+Gemma 3n models are designed for efficient execution on low-resource devices.
+They are capable of multimodal input, handling text, image, video, and audio
+input, and generating text outputs, with open weights for pre-trained and
+instruction-tuned variants. These models were trained with data in over 140
+spoken languages.
+
+Gemma 3n models use selective parameter activation technology to reduce resource
+requirements. This technique allows the models to operate at an effective size
+of 2B and 4B parameters, which is lower than the total number of parameters they
+contain. For more information on Gemma 3n's efficient parameter management
+technology, see the
+[Gemma 3n](https://ai.google.dev/gemma/docs/gemma-3n#parameters)
+page.
+
+### Inputs and outputs
+
+-   **Input:**
+    -   Text string, such as a question, a prompt, or a document to be
+        summarized
+    -   Images, normalized to 256x256, 512x512, or 768x768 resolution
+        and encoded to 256 tokens each
+    -   Audio data encoded to 6.25 tokens per second from a single channel
+    -   Total input context of 32K tokens
+-   **Output:**
+    -   Generated text in response to the input, such as an answer to a
+        question, analysis of image content, or a summary of a document
+    -   Total output length up to 32K tokens, subtracting the request
+        input tokens
+
+### Usage
+
+Below, there are some code snippets on how to get quickly started with running the model.
+You can copy the snippet from the section that is relevant for your use case.
+
+#### Transformers.js
+
+First, install the [Transformers.js](https://huggingface.co/docs/transformers.js) library.
+Gemma 3n is supported starting from transformers.js version 3.6.0.
+
+```sh
+npm i @huggingface/transformers
+```
+
+> [!WARNING]  
+> Due to the model's large size, we currently only support Node.js, Deno, and Bun execution.
+> In-browser WebGPU support is actively being worked on, so stay tuned for an update!
+
+
+**Example:** Caption an image
+
+```js
+import {
+  AutoProcessor,
+  AutoModelForImageTextToText,
+  load_image,
+  TextStreamer,
+} from "@huggingface/transformers";
+
+// Load processor and model
+const model_id = "onnx-community/gemma-3n-E2B-it-ONNX";
+const processor = await AutoProcessor.from_pretrained(model_id);
+const model = await AutoModelForImageTextToText.from_pretrained(model_id, {
+  dtype: {
+    embed_tokens: "q8",
+    audio_encoder: "q8",
+    vision_encoder: "fp16",
+    decoder_model_merged: "q4",
+  },
+  device: "cpu", // NOTE: WebGPU support coming soon!
+});
+
+// Prepare prompt
+const messages = [
+  {
+    role: "user",
+    content: [
+      { type: "image" },
+      { type: "text", text: "Describe this image in detail." },
+    ],
+  },
+];
+const prompt = processor.apply_chat_template(messages, {
+  add_generation_prompt: true,
+});
+
+// Prepare inputs
+const url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg";
+const image = await load_image(url);
+const audio = null;
+const inputs = await processor(prompt, image, audio, {
+  add_special_tokens: false,
+});
+
+// Generate output
+const outputs = await model.generate({
+  ...inputs,
+  max_new_tokens: 512,
+  do_sample: false,
+  streamer: new TextStreamer(processor.tokenizer, {
+    skip_prompt: true,
+    skip_special_tokens: false,
+    // callback_function: (text) => { /* Do something with the streamed output */ },
+  }),
+});
+
+// Decode output
+const decoded = processor.batch_decode(
+  outputs.slice(null, [inputs.input_ids.dims.at(-1), null]),
+  { skip_special_tokens: true },
+);
+console.log(decoded[0]);
+```
+
+<details>
+
+<summary>See example output</summary>
+
+```
+The image is a close-up, slightly macro shot of a cluster of vibrant pink cosmos flowers in full bloom. The flowers are the focal point, with their delicate, slightly ruffled petals radiating outwards. They have a soft, almost pastel pink hue, and their edges are subtly veined. 
+
+A small, dark-colored bee is actively visiting one of the pink flowers, its body positioned near the center of the bloom. The bee appears to be collecting pollen or nectar. 
+
+The flowers are attached to slender, brownish-green stems, and some of the surrounding foliage is visible in a blurred background, suggesting a natural outdoor setting. There are also hints of other flowers in the background, including some red ones, adding a touch of contrast to the pink. 
+
+The lighting in the image seems to be natural daylight, casting soft shadows and highlighting the textures of the petals and the bee. The overall impression is one of delicate beauty and the gentle activity of nature.
+```
+
+</details>
+
+**Example:** Transcribe audio
+
+```js
+import {
+  AutoProcessor,
+  AutoModelForImageTextToText,
+  TextStreamer,
+} from "@huggingface/transformers";
+import wavefile from "wavefile";
+
+// Load processor and model
+const model_id = "onnx-community/gemma-3n-E2B-it-ONNX";
+const processor = await AutoProcessor.from_pretrained(model_id);
+const model = await AutoModelForImageTextToText.from_pretrained(model_id, {
+  dtype: {
+    embed_tokens: "q8",
+    audio_encoder: "q4",
+    vision_encoder: "fp16",
+    decoder_model_merged: "q4",
+  },
+  device: "cpu", // NOTE: WebGPU support coming soon!
+});
+
+// Prepare prompt
+const messages = [
+  {
+    role: "user",
+    content: [
+      { type: "audio" },
+      { type: "text", text: "Transcribe this audio verbatim." },
+    ],
+  },
+];
+const prompt = processor.apply_chat_template(messages, {
+  add_generation_prompt: true,
+});
+
+// Prepare inputs
+const url = "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav";
+const buffer = Buffer.from(await fetch(url).then((x) => x.arrayBuffer()));
+const wav = new wavefile.WaveFile(buffer);
+wav.toBitDepth("32f"); // Pipeline expects input as a Float32Array
+wav.toSampleRate(processor.feature_extractor.config.sampling_rate);
+let audioData = wav.getSamples();
+if (Array.isArray(audioData)) {
+  if (audioData.length > 1) {
+    for (let i = 0; i < audioData[0].length; ++i) {
+      audioData[0][i] = (Math.sqrt(2) * (audioData[0][i] + audioData[1][i])) / 2;
+    }
+  }
+  audioData = audioData[0];
+}
+
+const image = null;
+const audio = audioData;
+const inputs = await processor(prompt, image, audio, {
+  add_special_tokens: false,
+});
+
+// Generate output
+const outputs = await model.generate({
+  ...inputs,
+  max_new_tokens: 512,
+  do_sample: false,
+  streamer: new TextStreamer(processor.tokenizer, {
+    skip_prompt: true,
+    skip_special_tokens: false,
+    // callback_function: (text) => { /* Do something with the streamed output */ },
+  }),
+});
+
+// Decode output
+const decoded = processor.batch_decode(
+  outputs.slice(null, [inputs.input_ids.dims.at(-1), null]),
+  { skip_special_tokens: true },
+);
+console.log(decoded[0]);
+```
+
+<details>
+
+<summary>See example output</summary>
+
+```
+And so, my fellow Americans, ask not what your country can do for you. Ask what you can do for your country.
+```
+
+</details>
+
+
+#### ONNXRuntime
+
+```py
+import onnxruntime
+import numpy as np
+from transformers import AutoConfig, AutoProcessor
+import os
+
+# 1. Load models
+## Load config and processor
+model_id = "google/gemma-3n-E2B-it"
+processor = AutoProcessor.from_pretrained(model_id)
+config = AutoConfig.from_pretrained(model_id)
+
+## Load sessions
+model_dir          = "/path/to/model/files/"
+embed_model_path   = os.path.join(model_dir, "onnx/embed_tokens_quantized.onnx")
+audio_model_path   = os.path.join(model_dir, "onnx/audio_encoder.onnx")
+vision_model_path  = os.path.join(model_dir, "onnx/vision_encoder.onnx")
+decoder_model_path = os.path.join(model_dir, "onnx/decoder_model_merged_q4.onnx")
+vision_session     = onnxruntime.InferenceSession(vision_model_path)
+audio_session      = onnxruntime.InferenceSession(audio_model_path)
+embed_session      = onnxruntime.InferenceSession(embed_model_path)
+decoder_session    = onnxruntime.InferenceSession(decoder_model_path)
+
+## Set config values
+num_key_value_heads = config.text_config.num_key_value_heads
+head_dim = config.text_config.head_dim
+num_hidden_layers = config.text_config.num_hidden_layers
+eos_token_id = 106 # != config.text_config.eos_token_id
+image_token_id = config.image_token_id
+audio_token_id = config.audio_token_id
+
+
+# 2. Prepare inputs
+## Create input messages
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "In detail, describe the following audio and image."},
+            {"type": "audio", "audio": "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav"},
+            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+        ],
+    },
+]
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+)
+input_ids = inputs["input_ids"].numpy()
+attention_mask = inputs["attention_mask"].numpy()
+position_ids = np.cumsum(attention_mask, axis=-1) - 1
+
+pixel_values = inputs["pixel_values"].numpy() if "pixel_values" in inputs else None
+input_features = inputs["input_features"].numpy().astype(np.float32) if "input_features" in inputs else None
+input_features_mask = inputs["input_features_mask"].numpy() if "input_features_mask" in inputs else None
+
+## Prepare decoder inputs
+batch_size = input_ids.shape[0]
+past_key_values = {
+    f"past_key_values.{layer}.{kv}": np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
+    for layer in range(num_hidden_layers)
+    for kv in ("key", "value")
+}
+
+# 3. Generation loop
+max_new_tokens = 1024
+generated_tokens = np.array([[]], dtype=np.int64)
+image_features = None
+audio_features = None
+for i in range(max_new_tokens):
+    inputs_embeds, per_layer_inputs = embed_session.run(None, {"input_ids": input_ids})
+    if image_features is None and pixel_values is not None:
+        image_features = vision_session.run(
+            ["image_features"],
+            {
+                "pixel_values": pixel_values,
+            }
+        )[0]
+        mask = (input_ids == image_token_id).reshape(-1)
+        flat_embeds = inputs_embeds.reshape(-1, inputs_embeds.shape[-1])
+        flat_embeds[mask] = image_features.reshape(-1, image_features.shape[-1])
+        inputs_embeds = flat_embeds.reshape(inputs_embeds.shape)
+
+    if audio_features is None and input_features is not None and input_features_mask is not None:
+        audio_features = audio_session.run(
+            ["audio_features"],
+            {
+                "input_features": input_features,
+                "input_features_mask": input_features_mask,
+            }
+        )[0]
+        mask = (input_ids == audio_token_id).reshape(-1)
+        flat_embeds = inputs_embeds.reshape(-1, inputs_embeds.shape[-1])
+        flat_embeds[mask] = audio_features.reshape(-1, audio_features.shape[-1])
+        inputs_embeds = flat_embeds.reshape(inputs_embeds.shape)
+
+    logits, *present_key_values = decoder_session.run(None, dict(
+        inputs_embeds=inputs_embeds,
+        per_layer_inputs=per_layer_inputs,
+        position_ids=position_ids,
+        **past_key_values,
+    ))
+
+    ## Update values for next generation loop
+    input_ids = logits[:, -1].argmax(-1, keepdims=True)
+    attention_mask = np.ones_like(input_ids)
+    position_ids = position_ids[:, -1:] + 1
+    for j, key in enumerate(past_key_values):
+        past_key_values[key] = present_key_values[j]
+
+    generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
+    if (input_ids == eos_token_id).all():
+        break
+
+    ## (Optional) Streaming
+    print(processor.decode(input_ids[0]), end="", flush=True)
+print()
+
+# 4. Output result
+print(processor.batch_decode(generated_tokens, skip_special_tokens=True)[0])
+```
+
+### Citation
+
+```
+@article{gemma_3n_2025,
+    title={Gemma 3n},
+    url={https://ai.google.dev/gemma/docs/gemma-3n},
+    publisher={Google DeepMind},
+    author={Gemma Team},
+    year={2025}
+}
+```
+
+## Model Data
+
+Data used for model training and how the data was processed.
+
+### Training Dataset
+
+These models were trained on a dataset that includes a wide variety of sources
+totalling approximately 11 trillion tokens. The knowledge cutoff date for the
+training data was June 2024. 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.
+    The training dataset includes content in over 140 languages.
+-   **Code**: Exposing the model to code helps it to learn the syntax and
+    patterns of programming languages, which improves its ability to generate
+    code and understand code-related questions.
+-   **Mathematics**: Training on mathematical text helps the model learn
+    logical reasoning, symbolic representation, and to address mathematical queries.
+-   **Images**: A wide range of images enables the model to perform image
+    analysis and visual data extraction tasks.
+-   Audio: A diverse set of sound samples enables the model to recognize
+    speech, transcribe text from recordings, and identify information in audio data.
+
+The combination of these diverse data sources is crucial for training a
+powerful multimodal model that can handle a wide variety of different tasks and
+data 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 safety in
+    line with
+    [our policies](https://ai.google/static/documents/ai-responsibility-update-published-february-2025.pdf).
+
+## Implementation Information
+
+Details about the model internals.
+
+### Hardware
+
+Gemma was trained using [Tensor Processing Unit
+(TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv4p, TPUv5p
+and TPUv5e). Training generative 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 generative models. 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/jax-ml/jax) and
+[ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/).
+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, 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://goo.gle/gemma2report):
+*"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 at full precision (float32) against a large
+collection of different datasets and metrics to cover different aspects of
+content generation. Evaluation results marked with **IT** are for
+instruction-tuned models. Evaluation results marked with **PT** are for
+pre-trained models.
+
+#### Reasoning and factuality
+
+| Benchmark                      | Metric         | n-shot   |  E2B PT  |  E4B PT  |
+| ------------------------------ |----------------|----------|:--------:|:--------:|
+| [HellaSwag][hellaswag]         | Accuracy       | 10-shot  |   72.2   |   78.6   |
+| [BoolQ][boolq]                 | Accuracy       | 0-shot   |   76.4   |   81.6   |
+| [PIQA][piqa]                   | Accuracy       | 0-shot   |   78.9   |   81.0   |
+| [SocialIQA][socialiqa]         | Accuracy       | 0-shot   |   48.8   |   50.0   |
+| [TriviaQA][triviaqa]           | Accuracy       | 5-shot   |   60.8   |   70.2   |
+| [Natural Questions][naturalq]  | Accuracy       | 5-shot   |   15.5   |   20.9   |
+| [ARC-c][arc]                   | Accuracy       | 25-shot  |   51.7   |   61.6   |
+| [ARC-e][arc]                   | Accuracy       | 0-shot   |   75.8   |   81.6   |
+| [WinoGrande][winogrande]       | Accuracy       | 5-shot   |   66.8   |   71.7   |
+| [BIG-Bench Hard][bbh]          | Accuracy       | few-shot |   44.3   |   52.9   |
+| [DROP][drop]                   | Token F1 score | 1-shot   |   53.9   |   60.8   |
+
+[hellaswag]: https://arxiv.org/abs/1905.07830
+[boolq]: https://arxiv.org/abs/1905.10044
+[piqa]: https://arxiv.org/abs/1911.11641
+[socialiqa]: https://arxiv.org/abs/1904.09728
+[triviaqa]: https://arxiv.org/abs/1705.03551
+[naturalq]: https://github.com/google-research-datasets/natural-questions
+[arc]: https://arxiv.org/abs/1911.01547
+[winogrande]: https://arxiv.org/abs/1907.10641
+[bbh]: https://paperswithcode.com/dataset/bbh
+[drop]: https://arxiv.org/abs/1903.00161
+
+#### Multilingual
+
+| Benchmark                           | Metric                  | n-shot   |  E2B IT  |  E4B IT  |
+| ------------------------------------|-------------------------|----------|:--------:|:--------:|
+| [MGSM][mgsm]                        | Accuracy                |  0-shot  |   53.1   |   60.7   |
+| [WMT24++][wmt24pp] (ChrF)           | Character-level F-score |  0-shot  |   42.7   |   50.1   |
+| [Include][include]                  | Accuracy                |  0-shot  |   38.6   |   57.2   |
+| [MMLU][mmlu] (ProX)                 | Accuracy                |  0-shot  |    8.1   |   19.9   |
+| [OpenAI MMLU][openai-mmlu]          | Accuracy                |  0-shot  |   22.3   |   35.6   |
+| [Global-MMLU][global-mmlu]          | Accuracy                |  0-shot  |   55.1   |   60.3   |
+| [ECLeKTic][eclektic]                | ECLeKTic score          |  0-shot  |    2.5   |    1.9   |
+
+[mgsm]: https://arxiv.org/abs/2210.03057
+[wmt24pp]: https://arxiv.org/abs/2502.12404v1
+[include]:https://arxiv.org/abs/2411.19799
+[mmlu]: https://arxiv.org/abs/2009.03300
+[openai-mmlu]: https://huggingface.co/datasets/openai/MMMLU
+[global-mmlu]: https://huggingface.co/datasets/CohereLabs/Global-MMLU
+[eclektic]: https://arxiv.org/abs/2502.21228
+
+#### STEM and code
+
+| Benchmark                           | Metric                   | n-shot   |  E2B IT  |  E4B IT  |
+| ------------------------------------|--------------------------|----------|:--------:|:--------:|
+| [GPQA][gpqa] Diamond                | RelaxedAccuracy/accuracy |  0-shot  |   24.8   |   23.7   |
+| [LiveCodeBench][lcb] v5             | pass@1                   |  0-shot  |   18.6   |   25.7   |
+| Codegolf v2.2                       | pass@1                   |  0-shot  |   11.0   |   16.8   |
+| [AIME 2025][aime-2025]              | Accuracy                 |  0-shot  |    6.7   |   11.6   |
+
+[gpqa]: https://arxiv.org/abs/2311.12022
+[lcb]: https://arxiv.org/abs/2403.07974
+[aime-2025]: https://www.vals.ai/benchmarks/aime-2025-05-09
+
+#### Additional benchmarks
+
+| Benchmark                            | Metric     | n-shot   |  E2B IT  |  E4B IT  |
+| ------------------------------------ |------------|----------|:--------:|:--------:|
+| [MMLU][mmlu]                         |  Accuracy  |  0-shot  |   60.1   |   64.9   |
+| [MBPP][mbpp]                         |  pass@1    |  3-shot  |   56.6   |   63.6   |
+| [HumanEval][humaneval]               |  pass@1    |  0-shot  |   66.5   |   75.0   |
+| [LiveCodeBench][lcb]                 |  pass@1    |  0-shot  |   13.2   |   13.2   |
+| HiddenMath                           |  Accuracy  |  0-shot  |   27.7   |   37.7   |
+| [Global-MMLU-Lite][global-mmlu-lite] |  Accuracy  |  0-shot  |   59.0   |   64.5   |
+| [MMLU][mmlu] (Pro)                   |  Accuracy  |  0-shot  |   40.5   |   50.6   |
+
+[gpqa]: https://arxiv.org/abs/2311.12022
+[mbpp]: https://arxiv.org/abs/2108.07732
+[humaneval]: https://arxiv.org/abs/2107.03374
+[lcb]: https://arxiv.org/abs/2403.07974
+[global-mmlu-lite]: https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite
+
+## 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:
+
+-   **Child Safety**: Evaluation of text-to-text and image to text prompts
+    covering child safety policies, including child sexual abuse and
+    exploitation.
+-   **Content Safety:** Evaluation of text-to-text and image to text prompts
+    covering safety policies including, harassment, violence and gore, and hate
+    speech.
+-   **Representational Harms**: Evaluation of text-to-text and image to text
+    prompts covering safety policies including bias, stereotyping, and harmful
+    associations or inaccuracies.
+
+In addition to development level evaluations, we conduct "assurance
+evaluations" which are our 'arms-length' internal evaluations for responsibility
+governance decision making. They are conducted separately from the model
+development team, to inform decision making about release. High level findings
+are fed back to the model team, but prompt sets are held-out to prevent
+overfitting and preserve the results' ability to inform decision making. Notable
+assurance evaluation results are reported to our Responsibility & Safety Council
+as part of release review.
+
+### Evaluation Results
+
+For all areas of safety testing, we saw safe levels of performance across the
+categories of child safety, content safety, and representational harms relative
+to previous Gemma models. All testing was conducted without safety filters to
+evaluate the model capabilities and behaviors. For text-to-text,  image-to-text,
+and audio-to-text, and across all model sizes, the model produced minimal policy
+violations, and showed significant improvements over previous Gemma models'
+performance with respect to high severity violations. A limitation of our
+evaluations was they included primarily English language prompts.
+
+## Usage and Limitations
+
+These models have certain limitations that users should be aware of.
+
+### Intended Usage
+
+Open generative models 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**: 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.
+    -   **Image Data Extraction**: Extract, interpret, and summarize
+        visual data for text communications.
+    -   **Audio Data Extraction**: Transcribe spoken language, translate speech
+        to text in other languages, and analyze sound-based data.
+-   Research and Education
+    -   **Natural Language Processing (NLP) and generative model
+        Research**: These models can serve as a foundation for researchers to
+        experiment with generative models and 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 data 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
+    -   Models 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. Models might struggle
+        to grasp subtle nuances, sarcasm, or figurative language.
+-   Factual Accuracy
+    -   Models 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
+    -   Models 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 generative models raises several ethical concerns. In
+creating an open model, we have carefully considered the following:
+
+-   Bias and Fairness
+    -   Generative models trained on large-scale, real-world text and image 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
+    -   Generative models 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](https://ai.google.dev/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 generative model 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
+    generative models. 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
+    certain personal information and other sensitive data. 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
+generative 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.

chat_template.jinja

@@ -0,0 +1,49 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'audio' -%}
+                {{ '<audio_soft_token>' }}
+            {%- elif item['type'] == 'image' -%}
+                {{ '<image_soft_token>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,194 @@
+{
+  "architectures": [
+    "Gemma3nForConditionalGeneration"
+  ],
+  "audio_config": {
+    "conf_attention_chunk_size": 12,
+    "conf_attention_context_left": 13,
+    "conf_attention_context_right": 0,
+    "conf_attention_invalid_logits_value": -1000000000.0,
+    "conf_attention_logit_cap": 50.0,
+    "conf_conv_kernel_size": 5,
+    "conf_num_attention_heads": 8,
+    "conf_num_hidden_layers": 12,
+    "conf_positional_bias_size": 256,
+    "conf_reduction_factor": 4,
+    "conf_residual_weight": 0.5,
+    "gradient_clipping": 10000000000.0,
+    "hidden_size": 1536,
+    "input_feat_size": 128,
+    "model_type": "gemma3n_audio",
+    "rms_norm_eps": 1e-06,
+    "sscp_conv_channel_size": [
+      128,
+      32
+    ],
+    "sscp_conv_eps": 0.001,
+    "sscp_conv_kernel_size": [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ]
+    ],
+    "sscp_conv_stride_size": [
+      [
+        2,
+        2
+      ],
+      [
+        2,
+        2
+      ]
+    ],
+    "torch_dtype": "float32",
+    "vocab_size": 128
+  },
+  "audio_soft_tokens_per_image": 188,
+  "audio_token_id": 262273,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "eoa_token_id": 262272,
+  "eoi_token_id": 262144,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 262145,
+  "initializer_range": 0.02,
+  "model_type": "gemma3n",
+  "text_config": {
+    "activation_sparsity_pattern": [
+      0.95,
+      0.95,
+      0.95,
+      0.95,
+      0.95,
+      0.95,
+      0.95,
+      0.95,
+      0.95,
+      0.95,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.0
+    ],
+    "altup_active_idx": 0,
+    "altup_coef_clip": 120.0,
+    "altup_correct_scale": true,
+    "altup_lr_multiplier": 1.0,
+    "altup_num_inputs": 4,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "final_logit_softcapping": 30.0,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2048,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "laurel_rank": 64,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3n_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 10,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": 512,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 262144
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0.dev0",
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "audio_encoder.onnx": 1,
+      "embed_tokens.onnx": 1,
+      "embed_tokens_fp16.onnx": 1,
+      "embed_tokens_int8.onnx": 1,
+      "embed_tokens_uint8.onnx": 1,
+      "embed_tokens_quantized.onnx": 2,
+      "decoder_model_merged.onnx": 1,
+      "decoder_model_merged_fp16.onnx": 1,
+      "vision_encoder.onnx": 1
+    },
+    "dtype": {
+      "embed_tokens": "q8",
+      "decoder_model_merged": "q4"
+    }
+  },
+  "vision_config": {
+    "architecture": "mobilenetv5_enc",
+    "do_pooling": true,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "label_names": [
+      "LABEL_0",
+      "LABEL_1"
+    ],
+    "model_type": "gemma3n_vision",
+    "num_classes": 2,
+    "torch_dtype": "float32",
+    "vocab_size": 128
+  },
+  "vision_soft_tokens_per_image": 256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.53.0.dev0"
+}

onnx/audio_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf2bd244e47512209e97dd03a8ced93b771aefbc7976e4dffa95dc26a46e834
+size 574186

onnx/audio_encoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ef1d1f5ca8fdf754ca310f4941810518ed9b5d95311071a2faa95f9317fb78
+size 2738092544

onnx/audio_encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b9f9743736f14a65fc90c36099d5d537a1f7630f6279b35367fa71e1c24c0a
+size 1369532994

onnx/audio_encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08cebb815f95957830f0e4c8ad5236633684193394d9fe78b03834de49af6d3
+size 685768656

onnx/audio_encoder_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc02b241faaa00e336191241e9a12692ef6e91a8c46333c149143eec69127bc
+size 429503628

onnx/audio_encoder_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032ea8b096cc786bd64fc91be0b289c1ec090d8bf7d4b66950c89c0024a0abf7
+size 386021189

onnx/audio_encoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97d41ceaf872e6c086a329c30f9cee65ac76e496b0f33d0063f084ce1b3ce63
+size 685768729

onnx/audio_encoder_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97d41ceaf872e6c086a329c30f9cee65ac76e496b0f33d0063f084ce1b3ce63
+size 685768729

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6667abc5aad8c619e32b97d5810e127a85993dc9bbddb5f6d4ac5552372ea725
+size 3097473

onnx/decoder_model_merged.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251cb348af5bdfa3dfc8927b4a3661fe982f44ea3d912958f353a53e23e59b18
+size 9685536768

onnx/decoder_model_merged_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17037e16fe8113d36e9abe0162a636a4fc83eef049f76cf3da00629186eb58a
+size 3124259

onnx/decoder_model_merged_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67701dd9c9f2ff9816f328857b823aa58cc5af76a252218390fe8446c6a626e9
+size 4842754048

onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7659477568fb3f5a435467b90aa37587b4c517e089c9c21001a9cecf1f332318
+size 1518206957

onnx/decoder_model_merged_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c322cb1383546c11d04cd1e4d221bbe9060e4a94963aa95052caf5c24576acab
+size 1367169309

onnx/embed_tokens.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8e909884c67470deb1f45cba980e9be920e1d462483aacc1f033e924b1b99b
+size 24096

onnx/embed_tokens.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41496f3e27c6e3a05c6b0a4c920ab5feb801a61573271e4e0dc8fe375aee307e
+size 10231756800

onnx/embed_tokens_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421caccd14d4b9c23f61777a411ec279be3b683ae167dd4f1f2c1311cf63ceea
+size 24294

onnx/embed_tokens_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1d95f6dc54561f482f63c36b952ebb42e19c218b210f82a35e621c1c791c42
+size 5115878400

onnx/embed_tokens_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb81b7edee8dd69a8dd2da128f538f036e8a8e195fbd88334d068eccc9b7a92
+size 37469

onnx/embed_tokens_int8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3681c4674f7a9d622f26de9facb2361f45d975c376cc84908ea51c4fdb2671
+size 2557949952

onnx/embed_tokens_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c825362923452ea0e84fe4ad36fc403435727fa6f70d7e62a25ce65b460ca596
+size 829132

onnx/embed_tokens_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042ac572db0ab810be89075850a33cbbae1e58a9f1725b9cfad2b1ac1afedb09
+size 584056832

onnx/embed_tokens_quantized.onnx_data_1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6255ac239a73db0da6a3f829b3105e0bafdd146ff5459cd57e8cb9746c5f3a
+size 2076180480

onnx/embed_tokens_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d08faa32d867b176039c7187670c680f0506c13d6ab017e5265d0c41d2fc4e
+size 37477

onnx/embed_tokens_uint8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd1802008b547d884a3f0ccf5577331bea0e12d44caca52cae491ecba801917
+size 2557949952

onnx/vision_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827bf4aeb6e6df7bd8034fd9d376c3e9bf2ee4529dc6e8e53df4be5b5feebfaa
+size 1243721

onnx/vision_encoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44bc629382fa2a35b4311cf5bb47e491153768b074d339e3b4f4c9781d82d032
+size 1194281728

onnx/vision_encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb287b5cf96471f082ad148e56b2a0ef998759d64e0515f41bcbdc96c294ccf1
+size 606875188

onnx/vision_encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319f0ad13f54efdb6444ab7756701cc9c729ea88b7164b2b0e565651f7e14ec3
+size 301671895

onnx/vision_encoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fa5670686d5e5b6ed1215033da5194e83cca4410fd134346f623900ca4ad1d
+size 300879908

onnx/vision_encoder_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49109faefd77424060d1bfc4037190a17a3634e3b05e639630d3f833bde0dff8
+size 301672063

preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "Gemma3nAudioFeatureExtractor",
+  "feature_size": 128,
+  "fft_length": 1024,
+  "fft_overdrive": true,
+  "frame_length": 512,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "input_scale_factor": 1.0,
+  "max_frequency": 7600.0,
+  "mel_floor": 1e-05,
+  "min_frequency": 125.0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "per_bin_mean": null,
+  "per_bin_stddev": null,
+  "preemphasis": 0.97,
+  "preemphasis_htk_flavor": true,
+  "processor_class": "Gemma3nProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": false,
+  "return_tensors": null,
+  "sampling_rate": 16000,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

processor_config.json

@@ -0,0 +1,5 @@
+{
+  "audio_seq_length": 188,
+  "image_seq_length": 256,
+  "processor_class": "Gemma3nProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "audio_token": "<audio_soft_token>",
+  "boa_token": "<start_of_audio>",
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoa_token": "<end_of_audio>",
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
+size 33442553