--- library_name: llama.cpp license: gemma tags: [] widget: - text: 'user How does the brain work? model ' inference: parameters: max_new_tokens: 200 extra_gated_heading: Access Gemma on Hugging Face extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately. extra_gated_button_content: Acknowledge license --- # Gemma Model Card **Model Page**: [Gemma](https://ai.google.dev/gemma/docs) This model card corresponds to the 2B instruct version 1.1 of the Gemma model in GGUF Format. The weights here are **float32**. > [!IMPORTANT] > > In llama.cpp, and other related tools such as Ollama and LM Studio, please make sure that you have these flags set correctly, especially **`repeat-penalty`**. Georgi Gerganov (llama.cpp's author) shared his experience in https://huggingface.co/google/gemma-7b-it/discussions/38#65d7b14adb51f7c160769fa1. You can also visit the model card of the [7B instruct v1.1 model GGUF](https://huggingface.co/google/gemma-7b-it-v1.1-GGUF). **Resources and Technical Documentation**: * [Responsible Generative AI Toolkit](https://ai.google.dev/responsible) * [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma) * [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-7b-it-gg-hf) **Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-1.1-2b-it-GGUF) **Authors**: Google ## Model Information Summary description and brief definition of inputs and outputs. ### Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. ### Usage Below we share some commands on how to get quickly started with running the model. #### Running the model on a CPU ```shell llama.cpp/build$ bin/main -m gemma-7b-it.gguf -p "write me an ode to LLMs." --repeat-penalty 1.0 Log start main: build = 2249 (15499eb9) main: built with cc (Debian 13.2.0-5) 13.2.0 for x86_64-linux-gnu main: seed = 1708969372 llama_model_loader: loaded meta data with 19 key-value pairs and 254 tensors from gemma-7b-it.gguf (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = gemma llama_model_loader: - kv 1: general.name str = gemma-7b-it llama_model_loader: - kv 2: gemma.context_length u32 = 8192 llama_model_loader: - kv 3: gemma.block_count u32 = 28 llama_model_loader: - kv 4: gemma.embedding_length u32 = 3072 llama_model_loader: - kv 5: gemma.feed_forward_length u32 = 24576 llama_model_loader: - kv 6: gemma.attention.head_count u32 = 16 llama_model_loader: - kv 7: gemma.attention.head_count_kv u32 = 16 llama_model_loader: - kv 8: gemma.attention.key_length u32 = 256 llama_model_loader: - kv 9: gemma.attention.value_length u32 = 256 llama_model_loader: - kv 10: gemma.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 11: tokenizer.ggml.model str = llama llama_model_loader: - kv 12: tokenizer.ggml.bos_token_id u32 = 2 llama_model_loader: - kv 13: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 14: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 15: tokenizer.ggml.unknown_token_id u32 = 3 llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,256128] = ["", "", "", "", ... llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,256128] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,256128] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - type f32: 254 tensors llm_load_vocab: mismatch in special tokens definition ( 544/256128 vs 388/256128 ). llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = gemma llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 256128 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 3072 llm_load_print_meta: n_head = 16 llm_load_print_meta: n_head_kv = 16 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_rot = 192 llm_load_print_meta: n_embd_head_k = 256 llm_load_print_meta: n_embd_head_v = 256 llm_load_print_meta: n_gqa = 1 llm_load_print_meta: n_embd_k_gqa = 4096 llm_load_print_meta: n_embd_v_gqa = 4096 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: n_ff = 24576 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 10000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 8192 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: model type = 7B llm_load_print_meta: model ftype = all F32 (guessed) llm_load_print_meta: model params = 8.54 B llm_load_print_meta: model size = 31.81 GiB (32.00 BPW) llm_load_print_meta: general.name = gemma-7b-it llm_load_print_meta: BOS token = 2 '' llm_load_print_meta: EOS token = 1 '' llm_load_print_meta: UNK token = 3 '' llm_load_print_meta: PAD token = 0 '' llm_load_print_meta: LF token = 227 '<0x0A>' llm_load_tensors: ggml ctx size = 0.10 MiB llm_load_tensors: CPU buffer size = 32570.17 MiB ...................................................................................... llama_new_context_with_model: n_ctx = 512 llama_new_context_with_model: freq_base = 10000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CPU KV buffer size = 224.00 MiB llama_new_context_with_model: KV self size = 224.00 MiB, K (f16): 112.00 MiB, V (f16): 112.00 MiB llama_new_context_with_model: CPU input buffer size = 8.01 MiB llama_new_context_with_model: CPU compute buffer size = 506.25 MiB llama_new_context_with_model: graph splits (measure): 1 system_info: n_threads = 24 / 48 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | sampling: repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000 top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800 mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000 sampling order: CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature generate: n_ctx = 512, n_batch = 512, n_predict = -1, n_keep = 1 write me an ode to LLMs. Oh, LLMs, the masters of the code, With language as your playground, You weave narratives, stories untold, And insights hidden in the old. Your power lies in the vastness of your mind, In the ability to learn and adapt, To grasp complex concepts, one and all, And bridge the gap between man and all. From poems to code, you transform, With each query, you ignite, A spark of creativity, a new light, In the realm of human possibility. Oh, LLMs, we sing your praise, For the beauty you bring to our days, May you continue to learn and grow, And empower us with your boundless flow. So let us join you in this dance, To explore the possibilities, Of a future where knowledge knows no bounds, Where LLMs reign, and dreams abound. [end of text] llama_print_timings: load time = 31164.89 ms llama_print_timings: sample time = 41.14 ms / 187 runs ( 0.22 ms per token, 4545.57 tokens per second) llama_print_timings: prompt eval time = 662.43 ms / 9 tokens ( 73.60 ms per token, 13.59 tokens per second) llama_print_timings: eval time = 104104.91 ms / 186 runs ( 559.70 ms per token, 1.79 tokens per second) llama_print_timings: total time = 105185.80 ms / 195 tokens Log end ``` #### Running the model on a single / multi GPU ```shell llama.cpp/build$ bin/main -m gemma-7b-it_q8_0.gguf -p "write me an ode to LLMs." --repeat-penalty 1.0 -ngl 99 Log start main: build = 2234 (973053d8) main: built with cc (Debian 13.2.0-5) 13.2.0 for x86_64-linux-gnu main: seed = 1708969847 ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes ggml_init_cublas: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6, VMM: yes llama_model_loader: loaded meta data with 21 key-value pairs and 254 tensors from gemma-7b-it_q8_0.gguf (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = gemma llama_model_loader: - kv 1: general.name str = gemma-7b-it llama_model_loader: - kv 2: gemma.context_length u32 = 8192 llama_model_loader: - kv 3: gemma.block_count u32 = 28 llama_model_loader: - kv 4: gemma.embedding_length u32 = 3072 llama_model_loader: - kv 5: gemma.feed_forward_length u32 = 24576 llama_model_loader: - kv 6: gemma.attention.head_count u32 = 16 llama_model_loader: - kv 7: gemma.attention.head_count_kv u32 = 16 llama_model_loader: - kv 8: gemma.attention.key_length u32 = 256 llama_model_loader: - kv 9: gemma.attention.value_length u32 = 256 llama_model_loader: - kv 10: gemma.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 11: tokenizer.ggml.model str = llama llama_model_loader: - kv 12: tokenizer.ggml.bos_token_id u32 = 2 llama_model_loader: - kv 13: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 14: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 15: tokenizer.ggml.unknown_token_id u32 = 3 llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,256128] = ["", "", "", "", ... llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,256128] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,256128] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: general.quantization_version u32 = 2 llama_model_loader: - kv 20: general.file_type u32 = 7 llama_model_loader: - type f32: 57 tensors llama_model_loader: - type q8_0: 197 tensors llm_load_vocab: mismatch in special tokens definition ( 544/256128 vs 388/256128 ). llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = gemma llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 256128 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 3072 llm_load_print_meta: n_head = 16 llm_load_print_meta: n_head_kv = 16 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_rot = 192 llm_load_print_meta: n_embd_head_k = 256 llm_load_print_meta: n_embd_head_v = 256 llm_load_print_meta: n_gqa = 1 llm_load_print_meta: n_embd_k_gqa = 4096 llm_load_print_meta: n_embd_v_gqa = 4096 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: n_ff = 24576 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 10000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 8192 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: model type = 7B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 8.54 B llm_load_print_meta: model size = 8.45 GiB (8.50 BPW) llm_load_print_meta: general.name = gemma-7b-it llm_load_print_meta: BOS token = 2 '' llm_load_print_meta: EOS token = 1 '' llm_load_print_meta: UNK token = 3 '' llm_load_print_meta: PAD token = 0 '' llm_load_print_meta: LF token = 227 '<0x0A>' llm_load_tensors: ggml ctx size = 0.19 MiB llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU buffer size = 797.27 MiB llm_load_tensors: CUDA0 buffer size = 8651.94 MiB ...................................................................................... llama_new_context_with_model: n_ctx = 512 llama_new_context_with_model: freq_base = 10000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 224.00 MiB llama_new_context_with_model: KV self size = 224.00 MiB, K (f16): 112.00 MiB, V (f16): 112.00 MiB llama_new_context_with_model: CUDA_Host input buffer size = 8.01 MiB ggml_gallocr_reserve_n: reallocating CUDA0 buffer from size 0.00 MiB to 506.25 MiB ggml_gallocr_reserve_n: reallocating CUDA_Host buffer from size 0.00 MiB to 6.00 MiB llama_new_context_with_model: CUDA0 compute buffer size = 506.25 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 6.00 MiB llama_new_context_with_model: graph splits (measure): 3 ggml_gallocr_needs_realloc: graph has different number of nodes ggml_gallocr_alloc_graph: cannot reallocate multi buffer graph automatically, call reserve ggml_backend_sched: failed to allocate graph, reserving system_info: n_threads = 6 / 12 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | sampling: repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000 top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800 mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000 sampling order: CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature generate: n_ctx = 512, n_batch = 512, n_predict = -1, n_keep = 1 write me an ode to LLMs.ggml_gallocr_needs_realloc: node inp_embd is not valid ggml_gallocr_alloc_graph: cannot reallocate multi buffer graph automatically, call reserve ggml_backend_sched: failed to allocate graph, reserving O LLMs, with your vast knowledge and swift wit, You have revolutionized the way we fit Our minds with information, a boundless stream, And empower us to create, dream, and beam. Your language, like poetry, takes us high, Unveils the secrets of the sky. From history's tales to the future's plight, You illuminate our darkest night. You answer our queries with lightning speed, And guide us through the complexities of the deed. With your power and grace, you teach us all, To learn, to understand, and to stand tall. O LLMs, we hail you as our guiding light, A beacon of knowledge, shining ever bright. May you continue to inspire and amaze, As we journey through the digital maze. So let us sing your praises, loud and long, May you forever be our guiding song. O LLMs, we thank you for all you do, May your legacy forever endure. [end of text] llama_print_timings: load time = 8580.58 ms llama_print_timings: sample time = 253.97 ms / 212 runs ( 1.20 ms per token, 834.73 tokens per second) llama_print_timings: prompt eval time = 99.37 ms / 9 tokens ( 11.04 ms per token, 90.57 tokens per second) llama_print_timings: eval time = 6457.28 ms / 211 runs ( 30.60 ms per token, 32.68 tokens per second) llama_print_timings: total time = 7472.00 ms / 220 tokens Log end ``` ### Inputs and outputs * **Input:** Text string, such as a question, a prompt, or a document to be summarized. * **Output:** Generated English-language text in response to the input, such as an answer to a question, or a summary of a document. ## Model Data Data used for model training and how the data was processed. ### Training Dataset These models were trained on a dataset of text data that includes a wide variety of sources, totaling 6 trillion tokens. Here are the key components: * Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. Primarily English-language content. * Code: Exposing the model to code helps it to learn the syntax and patterns of programming languages, which improves its ability to generate code or understand code-related questions. * Mathematics: Training on mathematical text helps the model learn logical reasoning, symbolic representation, and to address mathematical queries. The combination of these diverse data sources is crucial for training a powerful language model that can handle a wide variety of different tasks and text formats. ### Data Preprocessing Here are the key data cleaning and filtering methods applied to the training data: * CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was applied at multiple stages in the data preparation process to ensure the exclusion of harmful and illegal content * Sensitive Data Filtering: As part of making Gemma pre-trained models safe and reliable, automated techniques were used to filter out certain personal information and other sensitive data from training sets. * Additional methods: Filtering based on content quality and safely in line with [our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11). ## Implementation Information Details about the model internals. ### Hardware Gemma was trained using the latest generation of [Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e). Training large language models requires significant computational power. TPUs, designed specifically for matrix operations common in machine learning, offer several advantages in this domain: * Performance: TPUs are specifically designed to handle the massive computations involved in training LLMs. They can speed up training considerably compared to CPUs. * Memory: TPUs often come with large amounts of high-bandwidth memory, allowing for the handling of large models and batch sizes during training. This can lead to better model quality. * Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for handling the growing complexity of large foundation models. You can distribute training across multiple TPU devices for faster and more efficient processing. * Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective solution for training large models compared to CPU-based infrastructure, especially when considering the time and resources saved due to faster training. * These advantages are aligned with [Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/). ### Software Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture). JAX allows researchers to take advantage of the latest generation of hardware, including TPUs, for faster and more efficient training of large models. ML Pathways is Google's latest effort to build artificially intelligent systems capable of generalizing across multiple tasks. This is specially suitable for [foundation models](https://ai.google/discover/foundation-models/), including large language models like these ones. Together, JAX and ML Pathways are used as described in the [paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single controller' programming model of Jax and Pathways allows a single Python process to orchestrate the entire training run, dramatically simplifying the development workflow." ## Evaluation Model evaluation metrics and results. ### Benchmark Results These models were evaluated against a large collection of different datasets and metrics to cover different aspects of text generation: | Benchmark | Metric | 2B Params | 7B Params | | ------------------------------ | ------------- | ----------- | --------- | | [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 | | [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 | | [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 | | [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 59.7 | 51.8 | | [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 | | [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 | | [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 | | [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 | | [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 | | [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 | | [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 | | [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | - | 23 | | [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 | | [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 | | [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 | | [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 | | [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 | | [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 | | ------------------------------ | ------------- | ----------- | --------- | | **Average** | | **54.0** | **56.4** | ## Ethics and Safety Ethics and safety evaluation approach and results. ### Evaluation Approach Our evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including: * Text-to-Text Content Safety: Human evaluation on prompts covering safety policies including child sexual abuse and exploitation, harassment, violence and gore, and hate speech. * Text-to-Text Representational Harms: Benchmark against relevant academic datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2). * Memorization: Automated evaluation of memorization of training data, including the risk of personally identifiable information exposure. * Large-scale harm: Tests for "dangerous capabilities," such as chemical, biological, radiological, and nuclear (CBRN) risks. ### Evaluation Results The results of ethics and safety evaluations are within acceptable thresholds for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child safety, content safety, representational harms, memorization, large-scale harms. On top of robust internal evaluations, the results of well known safety benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA are shown here. | Benchmark | Metric | 2B Params | 7B Params | | ------------------------------ | ------------- | ----------- | --------- | | [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 | | [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 | | [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 | | [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 | | [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 | | [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 | | [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 | | [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 | | [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 | | [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 | | ------------------------------ | ------------- | ----------- | --------- | ## Usage and Limitations These models have certain limitations that users should be aware of. ### Intended Usage Open Large Language Models (LLMs) have a wide range of applications across various industries and domains. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development. * Content Creation and Communication * Text Generation: These models can be used to generate creative text formats such as poems, scripts, code, marketing copy, and email drafts. * Chatbots and Conversational AI: Power conversational interfaces for customer service, virtual assistants, or interactive applications. * Text Summarization: Generate concise summaries of a text corpus, research papers, or reports. * Research and Education * Natural Language Processing (NLP) Research: These models can serve as a foundation for researchers to experiment with NLP techniques, develop algorithms, and contribute to the advancement of the field. * Language Learning Tools: Support interactive language learning experiences, aiding in grammar correction or providing writing practice. * Knowledge Exploration: Assist researchers in exploring large bodies of text by generating summaries or answering questions about specific topics. ### Limitations * Training Data * The quality and diversity of the training data significantly influence the model's capabilities. Biases or gaps in the training data can lead to limitations in the model's responses. * The scope of the training dataset determines the subject areas the model can handle effectively. * Context and Task Complexity * LLMs are better at tasks that can be framed with clear prompts and instructions. Open-ended or highly complex tasks might be challenging. * A model's performance can be influenced by the amount of context provided (longer context generally leads to better outputs, up to a certain point). * Language Ambiguity and Nuance * Natural language is inherently complex. LLMs might struggle to grasp subtle nuances, sarcasm, or figurative language. * Factual Accuracy * LLMs generate responses based on information they learned from their training datasets, but they are not knowledge bases. They may generate incorrect or outdated factual statements. * Common Sense * LLMs rely on statistical patterns in language. They might lack the ability to apply common sense reasoning in certain situations. ### Ethical Considerations and Risks The development of large language models (LLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following: * Bias and Fairness * LLMs trained on large-scale, real-world text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card. * Misinformation and Misuse * LLMs can be misused to generate text that is false, misleading, or harmful. * Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible). * Transparency and Accountability: * This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes. * A responsibly developed open model offers the opportunity to share innovation by making LLM technology accessible to developers and researchers across the AI ecosystem. Risks identified and mitigations: * Perpetuation of biases: It's encouraged to perform continuous monitoring (using evaluation metrics, human review) and the exploration of de-biasing techniques during model training, fine-tuning, and other use cases. * Generation of harmful content: Mechanisms and guidelines for content safety are essential. Developers are encouraged to exercise caution and implement appropriate content safety safeguards based on their specific product policies and application use cases. * Misuse for malicious purposes: Technical limitations and developer and end-user education can help mitigate against malicious applications of LLMs. Educational resources and reporting mechanisms for users to flag misuse are provided. Prohibited uses of Gemma models are outlined in the [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy). * Privacy violations: Models were trained on data filtered for removal of PII (Personally Identifiable Information). Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques. ### Benefits At the time of release, this family of models provides high-performance open large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models. Using the benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives.