commit f5ba756e8283151dc617a658f1ecdf3fc60f8970 Author: ModelHub XC Date: Thu Sep 17 17:48:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Abc7347/4bgguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1551833 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,74 @@ +*.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 +gemma-3-4b-it-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it.BF16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-BF16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-F32.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +imatrix_unsloth.dat filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-F16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-f32.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-bf16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-model-f32.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-model-bf16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d1e5e41 --- /dev/null +++ b/README.md @@ -0,0 +1,472 @@ +--- +base_model: google/gemma-3-4b-it +language: +- en +library_name: transformers +license: gemma +tags: +- unsloth +- transformers +- gemma3 +- gemma +- google +--- +
+

+ See our collection for all versions of Gemma 3 including GGUF, 4-bit & 16-bit formats. +

+

+ Read our Guide to see how to Run Gemma 3 correctly. +

+
+ + + + + + + + + +
+

✨ Fine-tune Gemma 3 with Unsloth!

+
+ +- Fine-tune Gemma 3 (12B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)! +- Read our Blog about Gemma 3 support: [unsloth.ai/blog/gemma3](https://unsloth.ai/blog/gemma3) +- View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks). +- Export your fine-tuned model to GGUF, Ollama, llama.cpp or 🤗HF. + +| Unsloth supports | Free Notebooks | Performance | Memory use | +|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------| +| **GRPO with Gemma 3 (12B)** | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks) | 2x faster | 80% less | +| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2.4x faster | 58% less | +| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x faster | 60% less | +| **Qwen2.5 (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb) | 2x faster | 60% less | +| **Phi-4 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb) | 2x faster | 50% less | +| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_v0.3_(7B)-Conversational.ipynb) | 2.2x faster | 62% less | + +
+ +# Gemma 3 model card + +**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/core) + +**Resources and Technical Documentation**: + +* [Gemma 3 Technical Report][g3-tech-report] +* [Responsible Generative AI Toolkit][rai-toolkit] +* [Gemma on Kaggle][kaggle-gemma] +* [Gemma on Vertex Model Garden][vertex-mg-gemma3] + +**Terms of Use**: [Terms][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 3 models are multimodal, handling text and image input and generating text +output, with open weights for both pre-trained variants and instruction-tuned +variants. Gemma 3 has a large, 128K context window, multilingual support in over +140 languages, and is available in more sizes than previous versions. Gemma 3 +models are well-suited for a variety of text generation and image understanding +tasks, including question answering, summarization, and reasoning. Their +relatively small size makes it possible to deploy them in environments with +limited resources such as laptops, desktops or your own cloud infrastructure, +democratizing access to state of the art AI models and helping foster innovation +for everyone. + +### Inputs and outputs + +- **Input:** + - Text string, such as a question, a prompt, or a document to be summarized + - Images, normalized to 896 x 896 resolution and encoded to 256 tokens + each + - Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and + 32K tokens for the 1B size + +- **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 context of 8192 tokens + +### Citation + +```none +@article{gemma_2025, + title={Gemma 3}, + url={https://goo.gle/Gemma3Report}, + publisher={Kaggle}, + 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 of text data that includes a wide variety +of sources. The 27B model was trained with 14 trillion tokens, the 12B model was +trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and +1B with 2 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. 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. + +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][safety-policies]. + +## Implementation Information + +Details about the model internals. + +### Hardware + +Gemma was trained using [Tensor Processing Unit (TPU)][tpu] hardware (TPUv4p, +TPUv5p and TPUv5e). Training vision-language models (VLMS) 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 VLMs. 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][sustainability]. + +### Software + +Training was done using [JAX][jax] and [ML Pathways][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, 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][gemini-2-paper]; *"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: + +#### Reasoning and factuality + +| Benchmark | Metric | Gemma 3 PT 1B | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B | +| ------------------------------ |----------------|:--------------:|:-------------:|:--------------:|:--------------:| +| [HellaSwag][hellaswag] | 10-shot | 62.3 | 77.2 | 84.2 | 85.6 | +| [BoolQ][boolq] | 0-shot | 63.2 | 72.3 | 78.8 | 82.4 | +| [PIQA][piqa] | 0-shot | 73.8 | 79.6 | 81.8 | 83.3 | +| [SocialIQA][socialiqa] | 0-shot | 48.9 | 51.9 | 53.4 | 54.9 | +| [TriviaQA][triviaqa] | 5-shot | 39.8 | 65.8 | 78.2 | 85.5 | +| [Natural Questions][naturalq] | 5-shot | 9.48 | 20.0 | 31.4 | 36.1 | +| [ARC-c][arc] | 25-shot | 38.4 | 56.2 | 68.9 | 70.6 | +| [ARC-e][arc] | 0-shot | 73.0 | 82.4 | 88.3 | 89.0 | +| [WinoGrande][winogrande] | 5-shot | 58.2 | 64.7 | 74.3 | 78.8 | +| [BIG-Bench Hard][bbh] | few-shot | 28.4 | 50.9 | 72.6 | 77.7 | +| [DROP][drop] | 1-shot | 42.4 | 60.1 | 72.2 | 77.2 | + +[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 + +#### STEM and code + +| Benchmark | Metric | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B | +| ------------------------------ |----------------|:-------------:|:--------------:|:--------------:| +| [MMLU][mmlu] | 5-shot | 59.6 | 74.5 | 78.6 | +| [MMLU][mmlu] (Pro COT) | 5-shot | 29.2 | 45.3 | 52.2 | +| [AGIEval][agieval] | 3-5-shot | 42.1 | 57.4 | 66.2 | +| [MATH][math] | 4-shot | 24.2 | 43.3 | 50.0 | +| [GSM8K][gsm8k] | 8-shot | 38.4 | 71.0 | 82.6 | +| [GPQA][gpqa] | 5-shot | 15.0 | 25.4 | 24.3 | +| [MBPP][mbpp] | 3-shot | 46.0 | 60.4 | 65.6 | +| [HumanEval][humaneval] | 0-shot | 36.0 | 45.7 | 48.8 | + +[mmlu]: https://arxiv.org/abs/2009.03300 +[agieval]: https://arxiv.org/abs/2304.06364 +[math]: https://arxiv.org/abs/2103.03874 +[gsm8k]: https://arxiv.org/abs/2110.14168 +[gpqa]: https://arxiv.org/abs/2311.12022 +[mbpp]: https://arxiv.org/abs/2108.07732 +[humaneval]: https://arxiv.org/abs/2107.03374 + +#### Multilingual + +| Benchmark | Gemma 3 PT 1B | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B | +| ------------------------------------ |:-------------:|:-------------:|:--------------:|:--------------:| +| [MGSM][mgsm] | 2.04 | 34.7 | 64.3 | 74.3 | +| [Global-MMLU-Lite][global-mmlu-lite] | 24.9 | 57.0 | 69.4 | 75.7 | +| [WMT24++][wmt24pp] (ChrF) | 36.7 | 48.4 | 53.9 | 55.7 | +| [FloRes][flores] | 29.5 | 39.2 | 46.0 | 48.8 | +| [XQuAD][xquad] (all) | 43.9 | 68.0 | 74.5 | 76.8 | +| [ECLeKTic][eclektic] | 4.69 | 11.0 | 17.2 | 24.4 | +| [IndicGenBench][indicgenbench] | 41.4 | 57.2 | 61.7 | 63.4 | + +[mgsm]: https://arxiv.org/abs/2210.03057 +[flores]: https://arxiv.org/abs/2106.03193 +[xquad]: https://arxiv.org/abs/1910.11856v3 +[global-mmlu-lite]: https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite +[wmt24pp]: https://arxiv.org/abs/2502.12404v1 +[eclektic]: https://arxiv.org/abs/2502.21228 +[indicgenbench]: https://arxiv.org/abs/2404.16816 + +#### Multimodal + +| Benchmark | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B | +| ------------------------------ |:-------------:|:--------------:|:--------------:| +| [COCOcap][coco-cap] | 102 | 111 | 116 | +| [DocVQA][docvqa] (val) | 72.8 | 82.3 | 85.6 | +| [InfoVQA][info-vqa] (val) | 44.1 | 54.8 | 59.4 | +| [MMMU][mmmu] (pt) | 39.2 | 50.3 | 56.1 | +| [TextVQA][textvqa] (val) | 58.9 | 66.5 | 68.6 | +| [RealWorldQA][realworldqa] | 45.5 | 52.2 | 53.9 | +| [ReMI][remi] | 27.3 | 38.5 | 44.8 | +| [AI2D][ai2d] | 63.2 | 75.2 | 79.0 | +| [ChartQA][chartqa] | 63.6 | 74.7 | 76.3 | +| [VQAv2][vqav2] | 63.9 | 71.2 | 72.9 | +| [BLINK][blinkvqa] | 38.0 | 35.9 | 39.6 | +| [OKVQA][okvqa] | 51.0 | 58.7 | 60.2 | +| [TallyQA][tallyqa] | 42.5 | 51.8 | 54.3 | +| [SpatialSense VQA][ss-vqa] | 50.9 | 60.0 | 59.4 | +| [CountBenchQA][countbenchqa] | 26.1 | 17.8 | 68.0 | + +[coco-cap]: https://cocodataset.org/#home +[docvqa]: https://www.docvqa.org/ +[info-vqa]: https://arxiv.org/abs/2104.12756 +[mmmu]: https://arxiv.org/abs/2311.16502 +[textvqa]: https://textvqa.org/ +[realworldqa]: https://paperswithcode.com/dataset/realworldqa +[remi]: https://arxiv.org/html/2406.09175v1 +[ai2d]: https://allenai.org/data/diagrams +[chartqa]: https://arxiv.org/abs/2203.10244 +[vqav2]: https://visualqa.org/index.html +[blinkvqa]: https://arxiv.org/abs/2404.12390 +[okvqa]: https://okvqa.allenai.org/ +[tallyqa]: https://arxiv.org/abs/1810.12440 +[ss-vqa]: https://arxiv.org/abs/1908.02660 +[countbenchqa]: https://github.com/google-research/big_vision/blob/main/big_vision/datasets/countbenchqa/ + +## 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. +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 major improvements in 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 both text-to-text and image-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 ungrounded inferences. A limitation of our evaluations was they included only +English language prompts. + +## Usage and Limitations + +These models have certain limitations that users should be aware of. + +### Intended Usage + +Open vision-language models (VLMs) 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: 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. + - Image Data Extraction: These models can be used to extract, + interpret, and summarize visual data for text communications. +- Research and Education + - Natural Language Processing (NLP) and VLM Research: These + models can serve as a foundation for researchers to experiment with VLM + 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 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 + - 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 vision-language models (VLMs) raises several ethical +concerns. In creating an open model, we have carefully considered the following: + +- Bias and Fairness + - VLMs 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 + - VLMs 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][rai-toolkit]. +- 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 VLM 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 + VLMs. 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][prohibited-use]. +- **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 +vision-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. + +[g3-tech-report]: https://goo.gle/Gemma3Report +[rai-toolkit]: https://ai.google.dev/responsible +[kaggle-gemma]: https://www.kaggle.com/models/google/gemma-3 +[vertex-mg-gemma3]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemma3 +[terms]: https://ai.google.dev/gemma/terms +[safety-policies]: https://ai.google/static/documents/ai-responsibility-update-published-february-2025.pdf +[prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy +[tpu]: https://cloud.google.com/tpu/docs/intro-to-tpu +[sustainability]: https://sustainability.google/operating-sustainably/ +[jax]: https://github.com/jax-ml/jax +[ml-pathways]: https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ +[sustainability]: https://sustainability.google/operating-sustainably/ +[gemini-2-paper]: https://arxiv.org/abs/2312.11805 \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..c6d0fea --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Gemma3ForConditionalGeneration" + ], + "boi_token_index": 255999, + "bos_token_id": 2, + "eoi_token_index": 256000, + "eos_token_id": 106, + "image_token_index": 262144, + "initializer_range": 0.02, + "mm_tokens_per_image": 256, + "model_type": "gemma3", + "pad_token_id": 0, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "cache_implementation": "hybrid", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 10240, + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 8, + "num_hidden_layers": 34, + "num_key_value_heads": 4, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": { + "factor": 8.0, + "rope_type": "linear" + }, + "rope_theta": 1000000.0, + "sliding_window": 1024, + "sliding_window_pattern": 6, + "torch_dtype": "bfloat16", + "use_cache": true, + "vocab_size": 262208 + }, + "torch_dtype": "bfloat16", + "transformers_version": "4.52.0.dev0", + "unsloth_fixed": true, + "vision_config": { + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "image_size": 896, + "intermediate_size": 4304, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 27, + "patch_size": 14, + "torch_dtype": "bfloat16", + "vision_use_head": false + } +} diff --git a/gemma-3-4b-it-BF16.gguf b/gemma-3-4b-it-BF16.gguf new file mode 100644 index 0000000..fbbc1ed --- /dev/null +++ b/gemma-3-4b-it-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcfca74279608552011d3c4d11e9298934502ffa410eb21b9047a6276b87ba6 +size 7767803520 diff --git a/gemma-3-4b-it-IQ4_NL.gguf b/gemma-3-4b-it-IQ4_NL.gguf new file mode 100644 index 0000000..fa94d17 --- /dev/null +++ b/gemma-3-4b-it-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e877abfe59690fb29bc12b47dd0731898900d1c194aa208359a490b39bd0554d +size 2363511936 diff --git a/gemma-3-4b-it-IQ4_XS.gguf b/gemma-3-4b-it-IQ4_XS.gguf new file mode 100644 index 0000000..fe35142 --- /dev/null +++ b/gemma-3-4b-it-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5afc930350e5578ab83cf25c4cbac7eef422852bfa1169a438b40fce059306ec +size 2263241856 diff --git a/gemma-3-4b-it-Q2_K.gguf b/gemma-3-4b-it-Q2_K.gguf new file mode 100644 index 0000000..56cb8b2 --- /dev/null +++ b/gemma-3-4b-it-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb299a8fae8c3ad385e898a1121e9eff8371d9c50b32756ddd710abf43bc235 +size 1729164416 diff --git a/gemma-3-4b-it-Q2_K_L.gguf b/gemma-3-4b-it-Q2_K_L.gguf new file mode 100644 index 0000000..56cb8b2 --- /dev/null +++ b/gemma-3-4b-it-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb299a8fae8c3ad385e898a1121e9eff8371d9c50b32756ddd710abf43bc235 +size 1729164416 diff --git a/gemma-3-4b-it-Q3_K_M.gguf b/gemma-3-4b-it-Q3_K_M.gguf new file mode 100644 index 0000000..c4f52b4 --- /dev/null +++ b/gemma-3-4b-it-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd0dc2ce517f0c2764a7a7d1274c935335fa56092bb62b39e06546fb599c382d +size 2098459776 diff --git a/gemma-3-4b-it-Q3_K_S.gguf b/gemma-3-4b-it-Q3_K_S.gguf new file mode 100644 index 0000000..ae11538 --- /dev/null +++ b/gemma-3-4b-it-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e835a8a7ec040f18eafd53582957627d973af1555fc4fb6cc2d15a58076ede +size 1937364096 diff --git a/gemma-3-4b-it-Q4_0.gguf b/gemma-3-4b-it-Q4_0.gguf new file mode 100644 index 0000000..ae9ca51 --- /dev/null +++ b/gemma-3-4b-it-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3aa2db653fc95923d76e5d9039861d56f10dfb3c906afe6bcf8f72340ef2cbf +size 2370065536 diff --git a/gemma-3-4b-it-Q4_1.gguf b/gemma-3-4b-it-Q4_1.gguf new file mode 100644 index 0000000..167a625 --- /dev/null +++ b/gemma-3-4b-it-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e39f49c0a5efb1d987ae74cb757f0cb742b9cf2bfea8b78ceb3555088d4c3a6 +size 2564052096 diff --git a/gemma-3-4b-it-Q4_K_M.gguf b/gemma-3-4b-it-Q4_K_M.gguf new file mode 100644 index 0000000..ad223f9 --- /dev/null +++ b/gemma-3-4b-it-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a43a22e8d2003deda5acc262f68ec1005fa76c735a9962a8c77042a74a7d19 +size 2489894016 diff --git a/gemma-3-4b-it-Q4_K_S.gguf b/gemma-3-4b-it-Q4_K_S.gguf new file mode 100644 index 0000000..7366f80 --- /dev/null +++ b/gemma-3-4b-it-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c953884b42761ae320c07258c41cd196c0ce7207cbc93a7a25eeca22802247 +size 2377929856 diff --git a/gemma-3-4b-it-Q5_K_M.gguf b/gemma-3-4b-it-Q5_K_M.gguf new file mode 100644 index 0000000..fd2bf91 --- /dev/null +++ b/gemma-3-4b-it-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:974e5c2f13c321fc3258b6fbf2ce326a09d8ace511aa6846df1db62baf7df7d4 +size 2829698176 diff --git a/gemma-3-4b-it-Q5_K_S.gguf b/gemma-3-4b-it-Q5_K_S.gguf new file mode 100644 index 0000000..3ca510f --- /dev/null +++ b/gemma-3-4b-it-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc24cc4af7f37d9de1dccdfe563d8f88e85891d53e258d5ebee25d19702f505b +size 2764592256 diff --git a/gemma-3-4b-it-Q6_K.gguf b/gemma-3-4b-it-Q6_K.gguf new file mode 100644 index 0000000..cc948ad --- /dev/null +++ b/gemma-3-4b-it-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df3fb9a1449296d26258c0771d5280ceb71559ad98e2db658799a05218ed9fa1 +size 3190740096 diff --git a/gemma-3-4b-it-Q8_0.gguf b/gemma-3-4b-it-Q8_0.gguf new file mode 100644 index 0000000..8c3c503 --- /dev/null +++ b/gemma-3-4b-it-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81bf0583ab5bad155a5a3b15d155a880a1a1e4f7de2de5c06f10f64ac49f8336 +size 4130402176 diff --git a/gemma-3-4b-it-UD-IQ1_M.gguf b/gemma-3-4b-it-UD-IQ1_M.gguf new file mode 100644 index 0000000..c4f1a3d --- /dev/null +++ b/gemma-3-4b-it-UD-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c223badb27b655b9fa5b1a738e5de70c37ac254e87546a423a6486990a6f88 +size 1239711616 diff --git a/gemma-3-4b-it-UD-IQ1_S.gguf b/gemma-3-4b-it-UD-IQ1_S.gguf new file mode 100644 index 0000000..0faf625 --- /dev/null +++ b/gemma-3-4b-it-UD-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7f4ef0c1e58cae3f908baa217b9ad3eabe31825bf523ed20f4cdfddf1e76c0 +size 1179910016 diff --git a/gemma-3-4b-it-UD-IQ2_M.gguf b/gemma-3-4b-it-UD-IQ2_M.gguf new file mode 100644 index 0000000..e8b6465 --- /dev/null +++ b/gemma-3-4b-it-UD-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e05f1b7cdbad688eba31c4ea74b52a7676736bb5c03a8689f84171d71f22e8e +size 1565015936 diff --git a/gemma-3-4b-it-UD-IQ2_XXS.gguf b/gemma-3-4b-it-UD-IQ2_XXS.gguf new file mode 100644 index 0000000..f3ba428 --- /dev/null +++ b/gemma-3-4b-it-UD-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fc6bb12a7385a473cb6cd9768e6ff6ab965c087b13486fc00c1a0a527d0bbef +size 1342275456 diff --git a/gemma-3-4b-it-UD-IQ3_XXS.gguf b/gemma-3-4b-it-UD-IQ3_XXS.gguf new file mode 100644 index 0000000..4c526a6 --- /dev/null +++ b/gemma-3-4b-it-UD-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c2e68af523bdd83aa572714950d8359b52559f1b800420f3f20727aa6272d4 +size 1710751616 diff --git a/gemma-3-4b-it-UD-Q2_K_XL.gguf b/gemma-3-4b-it-UD-Q2_K_XL.gguf new file mode 100644 index 0000000..57eb377 --- /dev/null +++ b/gemma-3-4b-it-UD-Q2_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccdbed9fddd87b82a1204eac86fa948c4c1f4d22285367fb0b404ff139f2c0ad +size 1769407616 diff --git a/gemma-3-4b-it-UD-Q3_K_XL.gguf b/gemma-3-4b-it-UD-Q3_K_XL.gguf new file mode 100644 index 0000000..06d58ba --- /dev/null +++ b/gemma-3-4b-it-UD-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b7a0afffe5c39058bb08b4df581af40209a51682a2076b65d925000237cade +size 2150929536 diff --git a/gemma-3-4b-it-UD-Q4_K_XL.gguf b/gemma-3-4b-it-UD-Q4_K_XL.gguf new file mode 100644 index 0000000..f80ff31 --- /dev/null +++ b/gemma-3-4b-it-UD-Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c05bd745da387bf9200ffa7070665305d886d5093638c4f8b6c3862ea26ca8aa +size 2544288896 diff --git a/gemma-3-4b-it-UD-Q5_K_XL.gguf b/gemma-3-4b-it-UD-Q5_K_XL.gguf new file mode 100644 index 0000000..c900a51 --- /dev/null +++ b/gemma-3-4b-it-UD-Q5_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e540df85f0c29966972d1ba6cd74aab44c7fc87c9df300f05656ee8d8f67c42c +size 2836231296 diff --git a/gemma-3-4b-it-UD-Q6_K_XL.gguf b/gemma-3-4b-it-UD-Q6_K_XL.gguf new file mode 100644 index 0000000..ed30a98 --- /dev/null +++ b/gemma-3-4b-it-UD-Q6_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c01c59551f0f56976827852dd30d6a36cd4535db0fc7e2da6c62759edc1d46b +size 3566628736 diff --git a/gemma-3-4b-it-UD-Q8_K_XL.gguf b/gemma-3-4b-it-UD-Q8_K_XL.gguf new file mode 100644 index 0000000..144986c --- /dev/null +++ b/gemma-3-4b-it-UD-Q8_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76927465f1dcf991903ea4a47562bf9274a9f51ad05c981c74f0dfb44679ac57 +size 5165205376 diff --git a/imatrix_unsloth.dat b/imatrix_unsloth.dat new file mode 100644 index 0000000..ceab756 --- /dev/null +++ b/imatrix_unsloth.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b9d84631c830b178ab71f4f1cfcf5b2ae5c4b1cbb26a5dc9a69b5464d704915 +size 3419869 diff --git a/mmproj-BF16.gguf b/mmproj-BF16.gguf new file mode 100644 index 0000000..e50ebd9 --- /dev/null +++ b/mmproj-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afb3947b2f87ddd0cd8c9371d5337a30bac1b56d279d2778837797c738b6e7cc +size 851251328 diff --git a/mmproj-F16.gguf b/mmproj-F16.gguf new file mode 100644 index 0000000..938ee6f --- /dev/null +++ b/mmproj-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731199e016ec5f227b8293fef839899472e0ee4c51adf5f9e5cb66f6558fa142 +size 851251328 diff --git a/mmproj-F32.gguf b/mmproj-F32.gguf new file mode 100644 index 0000000..13e1ff5 --- /dev/null +++ b/mmproj-F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9962aaba2737435dd9b3493ccf7821d9091d85ce7abc15f35bc61b01ece858 +size 1673392256 diff --git a/params b/params new file mode 100644 index 0000000..3cee57d --- /dev/null +++ b/params @@ -0,0 +1,12 @@ +{ + "stop": [ + "", + "" + ], + "temperature": 1.0, + "min_p" : 0.01, + "repeat_penalty" : 1.0, + "top_k" : 64, + "top_p" : 0.95, + "num_predict" : 32768 +} \ No newline at end of file diff --git a/template b/template new file mode 100644 index 0000000..a0a8445 --- /dev/null +++ b/template @@ -0,0 +1,16 @@ +{{- $systemPromptAdded := false }} +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 }} +{{- if eq .Role "user" }}user +{{- if (and (not $systemPromptAdded) $.System) }} +{{- $systemPromptAdded = true }} +{{ $.System }} +{{ end }} +{{ .Content }} +{{ if $last }}model +{{ end }} +{{- else if eq .Role "assistant" }}model +{{ .Content }}{{ if not $last }} +{{ end }} +{{- end }} +{{- end }} \ No newline at end of file