初始化项目，由ModelHub XC社区提供模型

Model: Abc7347/12bgguf Source: Original Platform
2026-09-17 16:28:18 +08:00
commit 640cd44c01
35 changed files with 721 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,69 @@
+*.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-3-12b-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q6_K.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-3-12b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix_unsloth.dat filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj--BF16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-F16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,472 @@
+---
+base_model: google/gemma-3-12b-it
+language:
+- en
+library_name: transformers
+license: gemma
+tags:
+- unsloth
+- transformers
+- gemma3
+- gemma
+- google
+---
+<div>
+  <p style="margin-bottom: 0; margin-top: 0;">
+    <strong>See <a href="https://huggingface.co/collections/unsloth/gemma-3-67d12b7e8816ec6efa7e4e5b">our collection</a> for all versions of Gemma 3 including GGUF, 4-bit & 16-bit formats.</strong>
+  </p>
+  <p style="margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-gemma-3-effectively">Read our Guide</a> to see how to Run Gemma 3 correctly.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+<h1 style="margin-top: 0rem;">✨ Fine-tune Gemma 3 with Unsloth!</h1>
+</div>
+
+- 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 |
+
+<br>
+
+# 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
--- a/config.json
+++ 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": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "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
+  }
+}
--- a/gemma-3-12b-it-BF16.gguf
+++ b/gemma-3-12b-it-BF16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276920b11d80002d45b9b85291e333d9a7798df92b148ba9ae3d0625dd9f82f2
+size 23540151520
--- a/gemma-3-12b-it-IQ4_NL.gguf
+++ b/gemma-3-12b-it-IQ4_NL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63db34d705d70fb64d61357de9c6af9a1a65ae6f6e473d0f59e331b58c49715f
+size 6887164256
--- a/gemma-3-12b-it-IQ4_XS.gguf
+++ b/gemma-3-12b-it-IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e209a303d9d0841c1ab29a728b930ef630ba27766aa0067258f9e400f7ae8c65
+size 6550964576
--- a/gemma-3-12b-it-Q2_K.gguf
+++ b/gemma-3-12b-it-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e506f8ad03e46337f89aece60ab054ab70dfe60cc1fada17ef72edbedf8f8a9a
+size 4768221536
--- a/gemma-3-12b-it-Q2_K_L.gguf
+++ b/gemma-3-12b-it-Q2_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e506f8ad03e46337f89aece60ab054ab70dfe60cc1fada17ef72edbedf8f8a9a
+size 4768221536
--- a/gemma-3-12b-it-Q3_K_M.gguf
+++ b/gemma-3-12b-it-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ab409bfc66b1d48ed7d651cc1a8c56fcc9b347d03aa0ee833f5654b576a885
+size 6008818016
--- a/gemma-3-12b-it-Q3_K_S.gguf
+++ b/gemma-3-12b-it-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d72d010140472e81b92faf06e8ac9e365d885b0a03f7047159ace50514d440
+size 5458315616
--- a/gemma-3-12b-it-Q4_0.gguf
+++ b/gemma-3-12b-it-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80acb48f341b6c85744c1a45080a0de406a6f5449618f8ba5cde03fb5e1df5eb
+size 6909282656
--- a/gemma-3-12b-it-Q4_1.gguf
+++ b/gemma-3-12b-it-Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fb758273710422aaf94544fd4a206ff69084ab9f0e884957ad49efb6dbac8e
+size 7559563616
--- a/gemma-3-12b-it-Q4_K_M.gguf
+++ b/gemma-3-12b-it-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b8fd9d8672cd4240c178c217ca781409291f34e353d2e913b29c7602ceb3ff
+size 7300778336
--- a/gemma-3-12b-it-Q4_K_S.gguf
+++ b/gemma-3-12b-it-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d0712f25909254578c9eefddbdf30009e699d0ee8d9d2323689e0d6a925fe4
+size 6935333216
--- a/gemma-3-12b-it-Q5_K_M.gguf
+++ b/gemma-3-12b-it-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6d227c4983534b4661a0ada08328c21afa07c1e3c316fb55c172776cc808b3
+size 8445036896
--- a/gemma-3-12b-it-Q5_K_S.gguf
+++ b/gemma-3-12b-it-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa4cba108b49f5745cb48897c16fed1d96b384d011f9abd98136e0a608eebb5
+size 8231962976
--- a/gemma-3-12b-it-Q6_K.gguf
+++ b/gemma-3-12b-it-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a99903816f50b6b7d63fe96e1ed51d6e03c795051e99146719f3e066a863069
+size 9660811616
--- a/gemma-3-12b-it-Q8_0.gguf
+++ b/gemma-3-12b-it-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a774cd9c6f289a6159f4a3f92a7ebca887e15073f92016d53c3593cb440a5982
+size 12510212576
--- a/gemma-3-12b-it-UD-IQ1_M.gguf
+++ b/gemma-3-12b-it-UD-IQ1_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:285c6d06c44153cd70ef942ab71e908b99890086025557d454952edb3d2937ef
+size 3249207776
--- a/gemma-3-12b-it-UD-IQ1_S.gguf
+++ b/gemma-3-12b-it-UD-IQ1_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec1302aeb6c791838e66a6300e442c09ca74b45e9bef362a1ddfc0767741c77
+size 3057668576
--- a/gemma-3-12b-it-UD-IQ2_M.gguf
+++ b/gemma-3-12b-it-UD-IQ2_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9e8c2a2cd773e22e8e72c8d6ff36bcae542b9ce0291b41f0fad9a832b31d77
+size 4366371296
--- a/gemma-3-12b-it-UD-IQ2_XXS.gguf
+++ b/gemma-3-12b-it-UD-IQ2_XXS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aafbfdeef6af89585e45372292f79fa12baf143132924f578bb8519a2272e8d
+size 3604238816
--- a/gemma-3-12b-it-UD-IQ3_XXS.gguf
+++ b/gemma-3-12b-it-UD-IQ3_XXS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eddc5fdf75bc2f68ec389b4359d7b52af31b9024f5b7d1cc0f7db123450c80c5
+size 4834206176
--- a/gemma-3-12b-it-UD-Q2_K_XL.gguf
+++ b/gemma-3-12b-it-UD-Q2_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e9f7e21c0ef9a13ceeb63ecb1a7015e92ff6bd359a9356e3e9b02d880fe980
+size 4860535136
--- a/gemma-3-12b-it-UD-Q3_K_XL.gguf
+++ b/gemma-3-12b-it-UD-Q3_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b181d0c4b3e46c53ee4b31f2d8eba86dca0524da9cf688e0aa701525bf357b
+size 6142818656
--- a/gemma-3-12b-it-UD-Q4_K_XL.gguf
+++ b/gemma-3-12b-it-UD-Q4_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d0b2d09575a5ad04c71c61598d1a74b63d26db89cc6e379314ade5f3beb0b3
+size 7432229216
--- a/gemma-3-12b-it-UD-Q5_K_XL.gguf
+++ b/gemma-3-12b-it-UD-Q5_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d547d3cb4ba915d44eaf241d2aed59b518ad1a60915b94d7f06b1fdf40bace
+size 8462578016
--- a/gemma-3-12b-it-UD-Q6_K_XL.gguf
+++ b/gemma-3-12b-it-UD-Q6_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8d4ec90c93f70d73e978fa6c950f7c86e85724888fd0e2d18618bb7f4f70e9
+size 10556051936
--- a/gemma-3-12b-it-UD-Q8_K_XL.gguf
+++ b/gemma-3-12b-it-UD-Q8_K_XL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fedf9f286e58873315ececd1dfbb162e89205f6241219fa88f532ecff990a8a0
+size 14394193376
--- a/imatrix_unsloth.dat
+++ b/imatrix_unsloth.dat
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fddb827645217214c2560f93a6a3c49a9ab88a826d77479fbdc0777753021c83
+size 7433116
--- a/mmproj-BF16.gguf
+++ b/mmproj-BF16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f12a897e95aead276064e91b17792581d75fea4e246974fb81a8c7730422f9
+size 854200448
--- a/mmproj-F16.gguf
+++ b/mmproj-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de4ccfc379faa4cbf608dd365c028aa41f9774cdb1191d148d88910d1014f71
+size 854200448
--- a/mmproj-F32.gguf
+++ b/mmproj-F32.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abd89fef71f1f17b1ce7a8310a44e00a85f09bcede62498ddcb776f231a66ce
+size 1676341376
--- a/12
+++ b/12
@@ -0,0 +1,12 @@
+{
+    "stop": [
+        "<end_of_turn>",
+        "<eos>"
+    ],
+    "temperature": 0.1,
+    "min_p" : 0.01,
+    "repeat_penalty" : 1.0,
+    "top_k" : 64,
+    "top_p" : 0.95,
+    "num_predict" : 32768
+}
--- a/16
+++ b/16
@@ -0,0 +1,16 @@
+{{- $systemPromptAdded := false }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<start_of_turn>user
+{{- if (and (not $systemPromptAdded) $.System) }}
+{{- $systemPromptAdded = true }}
+{{ $.System }}
+{{ end }}
+{{ .Content }}<end_of_turn>
+{{ if $last }}<start_of_turn>model
+{{ end }}
+{{- else if eq .Role "assistant" }}<start_of_turn>model
+{{ .Content }}{{ if not $last }}<end_of_turn>
+{{ end }}
+{{- end }}
+{{- end }}