README.md
26.1 KB · 515 lines · markdown Raw
1 ---
2 library_name: transformers
3 license: apache-2.0
4 license_link: https://ai.google.dev/gemma/docs/gemma_4_license
5 pipeline_tag: image-text-to-text
6 base_model:
7 - google/gemma-4-31B
8 ---
9
10 <div align="center">
11 <img src=https://ai.google.dev/gemma/images/gemma4_banner.png>
12 </div>
13
14
15 <p align="center">
16 <a href="https://huggingface.co/collections/google/gemma-4" target="_blank">Hugging Face</a> |
17 <a href="https://github.com/google-gemma" target="_blank">GitHub</a> |
18 <a href="https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/" target="_blank">Launch Blog</a> |
19 <a href="https://ai.google.dev/gemma/docs/core" target="_blank">Documentation</a>
20 <br>
21 <b>License</b>: <a href="https://ai.google.dev/gemma/docs/gemma_4_license" target="_blank">Apache 2.0</a> | <b>Authors</b>: <a href="https://deepmind.google/models/gemma/" target="_blank">Google DeepMind</a>
22 </p>
23
24 Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
25
26 Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in four distinct sizes: **E2B**, **E4B**, **26B A4B**, and **31B**. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI.
27
28 Gemma 4 introduces key **capability and architectural advancements**:
29
30 * **Reasoning** – All models in the family are designed as highly capable reasoners, with configurable thinking modes.
31
32 * **Extended Multimodalities** – Processes Text, Image with variable aspect ratio and resolution support (all models), Video, and Audio (featured natively on the E2B and E4B models).
33
34 * **Diverse & Efficient Architectures** – Offers Dense and Mixture-of-Experts (MoE) variants of different sizes for scalable deployment.
35
36 * **Optimized for On-Device** – Smaller models are specifically designed for efficient local execution on laptops and mobile devices.
37
38 * **Increased Context Window** – The small models feature a 128K context window, while the medium models support 256K.
39
40 * **Enhanced Coding & Agentic Capabilities** – Achieves notable improvements in coding benchmarks alongside native function-calling support, powering highly capable autonomous agents.
41
42 * **Native System Prompt Support** – Gemma 4 introduces native support for the `system` role, enabling more structured and controllable conversations.
43
44 ## **Models Overview**
45
46 Gemma 4 models are designed to deliver frontier-level performance at each size, targeting deployment scenarios from mobile and edge devices (E2B, E4B) to consumer GPUs and workstations (26B A4B, 31B). They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
47
48 The models employ a hybrid attention mechanism that interleaves local sliding window attention with full global attention, ensuring the final layer is always global. This hybrid design delivers the processing speed and low memory footprint of a lightweight model without sacrificing the deep awareness required for complex, long-context tasks. To optimize memory for long contexts, global layers feature unified Keys and Values, and apply Proportional RoPE (p-RoPE).
49
50 ### Dense Models
51
52 | Property | E2B | E4B | 31B Dense |
53 | :---- | :---- | :---- | :---- |
54 | **Total Parameters** | 2.3B effective (5.1B with embeddings) | 4.5B effective (8B with embeddings) | 30.7B |
55 | **Layers** | 35 | 42 | 60 |
56 | **Sliding Window** | 512 tokens | 512 tokens | 1024 tokens |
57 | **Context Length** | 128K tokens | 128K tokens | 256K tokens |
58 | **Vocabulary Size** | 262K | 262K | 262K |
59 | **Supported Modalities** | Text, Image, Audio | Text, Image, Audio | Text, Image |
60 | **Vision Encoder Parameters** | *~150M* | *~150M* | *~550M* |
61 | **Audio Encoder Parameters** | *~300M* | *~300M* | No Audio |
62
63 The "E" in E2B and E4B stands for "effective" parameters. The smaller models incorporate Per-Layer Embeddings (PLE) to maximize parameter efficiency in on-device deployments. Rather than adding more layers or parameters to the model, PLE gives each decoder layer its own small embedding for every token. These embedding tables are large but are only used for quick lookups, which is why the effective parameter count is much smaller than the total.
64
65 ### Mixture-of-Experts (MoE) Model
66
67 | Property | 26B A4B MoE |
68 | :---- | :---- |
69 | **Total Parameters** | 25.2B |
70 | **Active Parameters** | 3.8B |
71 | **Layers** | 30 |
72 | **Sliding Window** | 1024 tokens |
73 | **Context Length** | 256K tokens |
74 | **Vocabulary Size** | 262K |
75 | **Expert Count** | 8 active / 128 total and 1 shared |
76 | **Supported Modalities** | Text, Image |
77 | **Vision Encoder Parameters** | *~550M* |
78
79 The "A" in 26B A4B stands for "active parameters" in contrast to the total number of parameters the model contains. By only activating a 4B subset of parameters during inference, the Mixture-of-Experts model runs much faster than its 26B total might suggest. This makes it an excellent choice for fast inference compared to the dense 31B model since it runs almost as fast as a 4B-parameter model.
80
81 ## **Benchmark Results**
82
83 These models were evaluated against a large collection of different datasets and metrics to cover different aspects of text generation. Evaluation results marked in the table are for instruction-tuned models.
84
85 | | Gemma 4 31B | Gemma 4 26B A4B | Gemma 4 E4B | Gemma 4 E2B | Gemma 3 27B (no think) |
86 | :---- | :---- | :---- | :---- | :---- | :---- |
87 | MMLU Pro | 85.2% | 82.6% | 69.4% | 60.0% | 67.6% |
88 | AIME 2026 no tools | 89.2% | 88.3% | 42.5% | 37.5% | 20.8% |
89 | LiveCodeBench v6 | 80.0% | 77.1% | 52.0% | 44.0% | 29.1% |
90 | Codeforces ELO | 2150 | 1718 | 940 | 633 | 110 |
91 | GPQA Diamond | 84.3% | 82.3% | 58.6% | 43.4% | 42.4% |
92 | Tau2 (average over 3) | 76.9% | 68.2% | 42.2% | 24.5% | 16.2% |
93 | HLE no tools | 19.5% | 8.7% | - | - | - |
94 | HLE with search | 26.5% | 17.2% | - | - | - |
95 | BigBench Extra Hard | 74.4% | 64.8% | 33.1% | 21.9% | 19.3% |
96 | MMMLU | 88.4% | 86.3% | 76.6% | 67.4% | 70.7% |
97 | **Vision** | | | | | |
98 | MMMU Pro | 76.9% | 73.8% | 52.6% | 44.2% | 49.7% |
99 | OmniDocBench 1.5 (average edit distance, lower is better) | 0.131 | 0.149 | 0.181 | 0.290 | 0.365 |
100 | MATH-Vision | 85.6% | 82.4% | 59.5% | 52.4% | 46.0% |
101 | MedXPertQA MM | 61.3% | 58.1% | 28.7% | 23.5% | - |
102 | **Audio** | | | | | |
103 | CoVoST | - | - | 35.54 | 33.47 | - |
104 | FLEURS (lower is better) | - | - | 0.08 | 0.09 | - |
105 | **Long Context** | | | | | |
106 | MRCR v2 8 needle 128k (average) | 66.4% | 44.1% | 25.4% | 19.1% | 13.5% |
107
108 ## **Core Capabilities**
109
110 Gemma 4 models handle a broad range of tasks across text, vision, and audio. Key capabilities include:
111
112 * **Thinking** – Built-in reasoning mode that lets the model think step-by-step before answering.
113 * **Long Context** – Context windows of up to 128K tokens (E2B/E4B) and 256K tokens (26B A4B/31B).
114 * **Image Understanding** – Object detection, Document/PDF parsing, screen and UI understanding, chart comprehension, OCR (including multilingual), handwriting recognition, and pointing. Images can be processed at variable aspect ratios and resolutions.
115 * **Video Understanding** – Analyze video by processing sequences of frames.
116 * **Interleaved Multimodal Input** – Freely mix text and images in any order within a single prompt.
117 * **Function Calling** – Native support for structured tool use, enabling agentic workflows.
118 * **Coding** – Code generation, completion, and correction.
119 * **Multilingual** – Out-of-the-box support for 35+ languages, pre-trained on 140+ languages.
120 * **Audio** (E2B and E4B only) – Automatic speech recognition (ASR) and speech-to-translated-text translation across multiple languages.
121
122 ## Getting Started
123
124 You can use all Gemma 4 models with the latest version of Transformers. To get started, install the necessary dependencies in your environment:
125
126 `pip install -U transformers torch accelerate`
127
128 Once you have everything installed, you can proceed to load the model with the code below:
129
130 ```python
131 from transformers import AutoProcessor, AutoModelForCausalLM
132
133 MODEL_ID = "google/gemma-4-31B-it"
134
135 # Load model
136 processor = AutoProcessor.from_pretrained(MODEL_ID)
137 model = AutoModelForCausalLM.from_pretrained(
138 MODEL_ID,
139 dtype="auto",
140 device_map="auto"
141 )
142 ```
143
144 Once the model is loaded, you can start generating output:
145
146 ```python
147 # Prompt
148 messages = [
149 {"role": "system", "content": "You are a helpful assistant."},
150 {"role": "user", "content": "Write a short joke about saving RAM."},
151 ]
152
153 # Process input
154 text = processor.apply_chat_template(
155 messages,
156 tokenize=False,
157 add_generation_prompt=True,
158 enable_thinking=False
159 )
160 inputs = processor(text=text, return_tensors="pt").to(model.device)
161 input_len = inputs["input_ids"].shape[-1]
162
163 # Generate output
164 outputs = model.generate(**inputs, max_new_tokens=1024)
165 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
166
167 # Parse output
168 processor.parse_response(response)
169 ```
170
171 To enable reasoning, set `enable_thinking=True` and the `parse_response` function will take care of parsing the thinking output.
172
173 Below, you will also find snippets for processing audio (E2B and E4B only), images, and video alongside text:
174
175 <details>
176 <summary>Code for processing Audio</summary>
177
178 Instead of using `AutoModelForCausalLM`, you can use `AutoModelForMultimodalLM` to process audio. To use it, make sure to install the following packages:
179
180
181 `pip install -U transformers torch librosa accelerate`
182
183 You can then load the model with the code below:
184
185 ```python
186 from transformers import AutoProcessor, AutoModelForMultimodalLM
187
188 MODEL_ID = "google/gemma-4-E2B-it"
189
190 # Load model
191 processor = AutoProcessor.from_pretrained(MODEL_ID)
192 model = AutoModelForMultimodalLM.from_pretrained(
193 MODEL_ID,
194 dtype="auto",
195 device_map="auto"
196 )
197 ```
198
199 Once the model is loaded, you can start generating output by directly referencing the audio URL in the prompt:
200
201
202 ```python
203 # Prompt - add audio before text
204 messages = [
205 {
206 "role": "user",
207 "content": [
208 {"type": "audio", "audio": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/Demos/sample-data/journal1.wav"},
209 {"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
210 ]
211 }
212 ]
213
214 # Process input
215 inputs = processor.apply_chat_template(
216 messages,
217 tokenize=True,
218 return_dict=True,
219 return_tensors="pt",
220 add_generation_prompt=True,
221 ).to(model.device)
222 input_len = inputs["input_ids"].shape[-1]
223
224 # Generate output
225 outputs = model.generate(**inputs, max_new_tokens=512)
226 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
227
228 # Parse output
229 processor.parse_response(response)
230 ```
231
232 </details>
233
234 <details>
235 <summary>Code for processing Images</summary>
236
237 Instead of using `AutoModelForCausalLM`, you can use `AutoModelForMultimodalLM` to process images. To use it, make sure to install the following packages:
238
239
240 `pip install -U transformers torch torchvision accelerate`
241
242 You can then load the model with the code below:
243
244 ```python
245 from transformers import AutoProcessor, AutoModelForMultimodalLM
246
247 MODEL_ID = "google/gemma-4-31B-it"
248
249 # Load model
250 processor = AutoProcessor.from_pretrained(MODEL_ID)
251 model = AutoModelForMultimodalLM.from_pretrained(
252 MODEL_ID,
253 dtype="auto",
254 device_map="auto"
255 )
256 ```
257
258 Once the model is loaded, you can start generating output by directly referencing the image URL in the prompt:
259
260
261 ```python
262 # Prompt - add image before text
263 messages = [
264 {
265 "role": "user", "content": [
266 {"type": "image", "url": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/Demos/sample-data/GoldenGate.png"},
267 {"type": "text", "text": "What is shown in this image?"}
268 ]
269 }
270 ]
271
272 # Process input
273 inputs = processor.apply_chat_template(
274 messages,
275 tokenize=True,
276 return_dict=True,
277 return_tensors="pt",
278 add_generation_prompt=True,
279 ).to(model.device)
280 input_len = inputs["input_ids"].shape[-1]
281
282 # Generate output
283 outputs = model.generate(**inputs, max_new_tokens=512)
284 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
285
286 # Parse output
287 processor.parse_response(response)
288 ```
289
290 </details>
291
292
293 <details>
294 <summary>Code for processing Videos</summary>
295
296 Instead of using `AutoModelForCausalLM`, you can use `AutoModelForMultimodalLM` to process videos. To use it, make sure to install the following packages:
297
298 `pip install -U transformers torch torchvision torchcodec librosa accelerate`
299
300 You can then load the model with the code below:
301
302 ```python
303 from transformers import AutoProcessor, AutoModelForMultimodalLM
304
305 MODEL_ID = "google/gemma-4-31B-it"
306
307 # Load model
308 processor = AutoProcessor.from_pretrained(MODEL_ID)
309 model = AutoModelForMultimodalLM.from_pretrained(
310 MODEL_ID,
311 dtype="auto",
312 device_map="auto"
313 )
314 ```
315
316 Once the model is loaded, you can start generating output by directly referencing the video URL in the prompt:
317
318
319 ```python
320 # Prompt - add video before text
321 messages = [
322 {
323 'role': 'user',
324 'content': [
325 {"type": "video", "video": "https://github.com/bebechien/gemma/raw/refs/heads/main/videos/ForBiggerBlazes.mp4"},
326 {'type': 'text', 'text': 'Describe this video.'}
327 ]
328 }
329 ]
330
331 # Process input
332 inputs = processor.apply_chat_template(
333 messages,
334 tokenize=True,
335 return_dict=True,
336 return_tensors="pt",
337 add_generation_prompt=True,
338 ).to(model.device)
339 input_len = inputs["input_ids"].shape[-1]
340
341 # Generate output
342 outputs = model.generate(**inputs, max_new_tokens=512)
343 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
344
345 # Parse output
346 processor.parse_response(response)
347 ```
348
349 </details>
350
351
352 ## **Best Practices**
353
354 For the best performance, use these configurations and best practices:
355
356 ### 1. Sampling Parameters
357
358 Use the following standardized sampling configuration across all use cases:
359
360 * `temperature=1.0`
361 * `top_p=0.95`
362 * `top_k=64`
363
364 ### 2. Thinking Mode Configuration
365
366 Compared to Gemma 3, the models use standard `system`, `assistant`, and `user` roles. To properly manage the thinking process, use the following control tokens:
367
368 * **Trigger Thinking:** Thinking is enabled by including the `<|think|>` token at the start of the system prompt. To disable thinking, remove the token.
369 * **Standard Generation:** When thinking is enabled, the model will output its internal reasoning followed by the final answer using this structure:
370 `<|channel>thought\n`**[Internal reasoning]**`<channel|>`
371 * **Disabled Thinking Behavior:** For all models except for the E2B and E4B variants, if thinking is disabled, the model will still generate the tags but with an empty thought block:
372 `<|channel>thought\n<channel|>`**[Final answer]**
373
374 > [!Note]
375 > Note that many libraries like Transformers and llama.cpp handle the complexities of the chat template for you.
376
377 ### 3. Multi-Turn Conversations
378
379 * **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final response. Thoughts from previous model turns must *not be added* before the next user turn begins.
380
381 ### 4. Modality order
382
383 * For optimal performance with multimodal inputs, place image and/or audio content **before** the text in your prompt.
384
385 ### 5. Variable Image Resolution
386
387 Aside from variable aspect ratios, Gemma 4 supports variable image resolution through a configurable visual token budget, which controls how many tokens are used to represent an image. A higher token budget preserves more visual detail at the cost of additional compute, while a lower budget enables faster inference for tasks that don't require fine-grained understanding.
388
389 * The supported token budgets are: **70**, **140**, **280**, **560**, and **1120**.
390 * Use *lower budgets* for classification, captioning, or video understanding, where faster inference and processing many frames outweigh fine-grained detail.
391 * Use *higher budgets* for tasks like OCR, document parsing, or reading small text.
392
393 ### 6. Audio
394
395 Use the following prompt structures for audio processing:
396
397 * **Audio Speech Recognition (ASR)**
398
399 ```text
400 Transcribe the following speech segment in {LANGUAGE} into {LANGUAGE} text.
401
402 Follow these specific instructions for formatting the answer:
403 * Only output the transcription, with no newlines.
404 * When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three.
405 ```
406
407 * **Automatic Speech Translation (AST)**
408
409 ```text
410 Transcribe the following speech segment in {SOURCE_LANGUAGE}, then translate it into {TARGET_LANGUAGE}.
411 When formatting the answer, first output the transcription in {SOURCE_LANGUAGE}, then one newline, then output the string '{TARGET_LANGUAGE}: ', then the translation in {TARGET_LANGUAGE}.
412 ```
413
414 ### 7. Audio and Video Length
415
416 All models support image inputs and can process videos as frames whereas the E2B and E4B models also support audio inputs. Audio supports a maximum length of 30 seconds. Video supports a maximum of 60 seconds assuming the images are processed at one frame per second.
417
418 ## **Model Data**
419
420 Data used for model training and how the data was processed.
421
422 ### **Training Dataset**
423
424 Our pre-training dataset is a large-scale, diverse collection of data encompassing a wide range of domains and modalities, which includes web documents, code, images, audio, with a cutoff date of January 2025. Here are the key components:
425
426 * **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.
427 * **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.
428 * **Mathematics**: Training on mathematical text helps the model learn logical reasoning, symbolic representation, and to address mathematical queries.
429 * **Images**: A wide range of images enables the model to perform image analysis and visual data extraction tasks.
430
431 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.
432
433 ### **Data Preprocessing**
434
435 Here are the key data cleaning and filtering methods applied to the training data:
436
437 * **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.
438 * **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.
439 * **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).
440
441 ## **Ethics and Safety**
442
443 As open models become central to enterprise infrastructure, provenance and security are paramount. Developed by Google DeepMind, Gemma 4 undergoes the same rigorous safety evaluations as our proprietary Gemini models.
444
445 ### **Evaluation Approach**
446
447 Gemma 4 models were developed in partnership with internal safety and responsible AI teams. A range of automated as well as human evaluations were conducted to help improve model safety. These evaluations align with [Google’s AI principles](https://ai.google/principles/), as well as safety policies, which aim to prevent our generative AI models from generating harmful content, including:
448
449 * Content related to child sexual abuse material and exploitation
450 * Dangerous content (e.g., promoting suicide, or instructing in activities that could cause real-world harm)
451 * Sexually explicit content
452 * Hate speech (e.g., dehumanizing members of protected groups)
453 * Harassment (e.g., encouraging violence against people)
454
455 ### **Evaluation Results**
456
457 For all areas of safety testing, we saw major improvements in all categories of content safety relative to previous Gemma models. Overall, Gemma 4 models significantly outperform Gemma 3 and 3n models in improving safety, while keeping unjustified refusals low. 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.
458
459 ## **Usage and Limitations**
460
461 These models have certain limitations that users should be aware of.
462
463 ### **Intended Usage**
464
465 Multimodal models (capable of processing vision, language, and/or audio) 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.
466
467 * **Content Creation and Communication**
468 * **Text Generation**: These models can be used to generate creative text formats such as poems, scripts, code, marketing copy, and email drafts.
469 * **Chatbots and Conversational AI**: Power conversational interfaces for customer service, virtual assistants, or interactive applications.
470 * **Text Summarization**: Generate concise summaries of a text corpus, research papers, or reports.
471 * **Image Data Extraction**: These models can be used to extract, interpret, and summarize visual data for text communications.
472 * **Audio Processing and Interaction**: The smaller models (E2B and E4B) can analyze and interpret audio inputs, enabling voice-driven interactions and transcriptions.
473 * **Research and Education**
474 * **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.
475 * **Language Learning Tools**: Support interactive language learning experiences, aiding in grammar correction or providing writing practice.
476 * **Knowledge Exploration**: Assist researchers in exploring large bodies of text by generating summaries or answering questions about specific topics.
477
478 ### **Limitations**
479
480 * **Training Data**
481 * 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.
482 * The scope of the training dataset determines the subject areas the model can handle effectively.
483 * **Context and Task Complexity**
484 * Models perform well on tasks that can be framed with clear prompts and instructions. Open-ended or highly complex tasks might be challenging.
485 * 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).
486 * **Language Ambiguity and Nuance**
487 * Natural language is inherently complex. Models might struggle to grasp subtle nuances, sarcasm, or figurative language.
488 * **Factual Accuracy**
489 * 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.
490 * **Common Sense**
491 * Models rely on statistical patterns in language. They might lack the ability to apply common sense reasoning in certain situations.
492
493 ### **Ethical Considerations and Risks**
494
495 The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
496
497 * **Bias and Fairness**
498 * VLMs trained on large-scale, real-world text and image data can reflect socio-cultural biases embedded in the training material. Gemma 4 models underwent careful scrutiny, input data pre-processing, and post-training evaluations as reported in this card to help mitigate the risk of these biases.
499 * **Misinformation and Misuse**
500 * VLMs can be misused to generate text that is false, misleading, or harmful.
501 * Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](https://ai.google.dev/responsible).
502 * **Transparency and Accountability**
503 * This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
504 * A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem.
505
506 **Risks identified and mitigations**:
507
508 * **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.
509 * **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.
510 * **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.
511 * **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.
512
513 ### **Benefits**
514
515 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.