commit 8eebd4629d61246478f13402f3f16e415fa15968 Author: ModelHub XC Date: Sun Jul 26 13:49:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/gemma-2-9b-it Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1e86ce --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +transformers/transformers-4.42.0.dev0-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..94c2536 --- /dev/null +++ b/README.md @@ -0,0 +1,824 @@ +--- +language: +- en +base_model: +- google/gemma-2-9b-it +pipeline_tag: text-generation +tags: +- gemma +- gemma2 +- conversational +- text-generation-inference +license: gemma +license_name: gemma +name: RedHatAI/gemma-2-9b-it +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 for both pre-trained variants and instruction-tuned variants. +readme: https://huggingface.co/RedHatAI/gemma-2-9b-it/main/README.md +tasks: +- text-to-text +provider: Google +license_link: https://ai.google.dev/gemma/terms +validated_on: + - RHOAI 2.20 + - RHAIIS 3.0 + - RHELAI 1.5 + - vLLM 0.8.4 +--- + +# Gemma 2 model card +

+ gemma-2-9b-it + Model Icon +

+ + +Validated Badge + + +**Validated on:** RHOAI 2.20, RHAIIS 3.0, RHELAI 1.5 + +**Model Page**: [Gemma](https://ai.google.dev/gemma/docs) + +**Resources and Technical Documentation**: + +* [Responsible Generative AI Toolkit][rai-toolkit] +* [Gemma on Kaggle][kaggle-gemma] +* [Gemma on Vertex Model Garden][vertex-mg-gemma] + +**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-9b-it) + +**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 for both 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 code snippets on how to get quickly started with running the model. First, install the Transformers library with: +```sh +pip install -U transformers +``` + +Then, copy the snippet from the section that is relevant for your usecase. + +## Deployment + +This model can be deployed efficiently on vLLM, Red Hat Enterprise Linux AI, and Openshift AI, as shown in the example below. + +Deploy on vLLM + +```python +from vllm import LLM, SamplingParams +from transformers import AutoTokenizer +model_id = "RedHatAI/gemma-2-9b-it" +number_gpus = 4 +sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256) +tokenizer = AutoTokenizer.from_pretrained(model_id) +prompt = "Give me a short introduction to large language model." +llm = LLM(model=model_id, tensor_parallel_size=number_gpus) +outputs = llm.generate(prompt, sampling_params) +generated_text = outputs[0].outputs[0].text +print(generated_text) +``` + +vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + +
+ Deploy on Red Hat AI Inference Server + +```bash +podman run --rm -it --device nvidia.com/gpu=all -p 8000:8000 \ + --ipc=host \ +--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \ +--env "HF_HUB_OFFLINE=0" -v ~/.cache/vllm:/home/vllm/.cache \ +--name=vllm \ +registry.access.redhat.com/rhaiis/rh-vllm-cuda \ +vllm serve \ +--tensor-parallel-size 8 \ +--max-model-len 32768 \ +--enforce-eager --model RedHatAI/gemma-2-9b-it +``` +​​See [Red Hat AI Inference Server documentation](https://docs.redhat.com/en/documentation/red_hat_ai_inference_server/) for more details. +
+ +
+ Deploy on Red Hat Enterprise Linux AI + +```bash +# Download model from Red Hat Registry via docker +# Note: This downloads the model to ~/.cache/instructlab/models unless --model-dir is specified. +ilab model download --repository docker://registry.redhat.io/rhelai1/gemma-2-9b-it:1.5 +``` + +```bash +# Serve model via ilab +ilab model serve --model-path ~/.cache/instructlab/models/gemma-2-9b-it + +# Chat with model +ilab model chat --model ~/.cache/instructlab/models/gemma-2-9b-it +``` +See [Red Hat Enterprise Linux AI documentation](https://docs.redhat.com/en/documentation/red_hat_enterprise_linux_ai/1.4) for more details. +
+ +
+ Deploy on Red Hat Openshift AI + +```python +# Setting up vllm server with ServingRuntime +# Save as: vllm-servingruntime.yaml +apiVersion: serving.kserve.io/v1alpha1 +kind: ServingRuntime +metadata: + name: vllm-cuda-runtime # OPTIONAL CHANGE: set a unique name + annotations: + openshift.io/display-name: vLLM NVIDIA GPU ServingRuntime for KServe + opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]' + labels: + opendatahub.io/dashboard: 'true' +spec: + annotations: + prometheus.io/port: '8080' + prometheus.io/path: '/metrics' + multiModel: false + supportedModelFormats: + - autoSelect: true + name: vLLM + containers: + - name: kserve-container + image: quay.io/modh/vllm:rhoai-2.20-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.20-rocm + command: + - python + - -m + - vllm.entrypoints.openai.api_server + args: + - "--port=8080" + - "--model=/mnt/models" + - "--served-model-name={{.Name}}" + env: + - name: HF_HOME + value: /tmp/hf_home + ports: + - containerPort: 8080 + protocol: TCP +``` + +```python +# Attach model to vllm server. This is an NVIDIA template +# Save as: inferenceservice.yaml +apiVersion: serving.kserve.io/v1beta1 +kind: InferenceService +metadata: + annotations: + openshift.io/display-name: gemma-2-9b-it # OPTIONAL CHANGE + serving.kserve.io/deploymentMode: RawDeployment + name: gemma-2-9b-it # specify model name. This value will be used to invoke the model in the payload + labels: + opendatahub.io/dashboard: 'true' +spec: + predictor: + maxReplicas: 1 + minReplicas: 1 + model: + modelFormat: + name: vLLM + name: '' + resources: + limits: + cpu: '2' # this is model specific + memory: 8Gi # this is model specific + nvidia.com/gpu: '1' # this is accelerator specific + requests: # same comment for this block + cpu: '1' + memory: 4Gi + nvidia.com/gpu: '1' + runtime: vllm-cuda-runtime # must match the ServingRuntime name above + storageUri: oci://registry.redhat.io/rhelai1/modelcar-gemma-2-9b-it:1.5 + tolerations: + - effect: NoSchedule + key: nvidia.com/gpu + operator: Exists +``` + +```bash +# make sure first to be in the project where you want to deploy the model +# oc project +# apply both resources to run model +# Apply the ServingRuntime +oc apply -f vllm-servingruntime.yaml +# Apply the InferenceService +oc apply -f qwen-inferenceservice.yaml +``` + +```python +# Replace and below: +# - Run `oc get inferenceservice` to find your URL if unsure. +# Call the server using curl: +curl https://-predictor-default./v1/chat/completions + -H "Content-Type: application/json" \ + -d '{ + "model": "gemma-2-9b-it", + "stream": true, + "stream_options": { + "include_usage": true + }, + "max_tokens": 1, + "messages": [ + { + "role": "user", + "content": "How can a bee fly when its wings are so small?" + } + ] +}' +``` + +See [Red Hat Openshift AI documentation](https://docs.redhat.com/en/documentation/red_hat_openshift_ai/2025) for more details. +
+ + + +#### Running with the `pipeline` API + +```python +import torch +from transformers import pipeline + +pipe = pipeline( + "text-generation", + model="google/gemma-2-9b-it", + model_kwargs={"torch_dtype": torch.bfloat16}, + device="cuda", # replace with "mps" to run on a Mac device +) + +messages = [ + {"role": "user", "content": "Who are you? Please, answer in pirate-speak."}, +] + +outputs = pipe(messages, max_new_tokens=256) +assistant_response = outputs[0]["generated_text"][-1]["content"].strip() +print(assistant_response) +# Ahoy, matey! I be Gemma, a digital scallywag, a language-slingin' parrot of the digital seas. I be here to help ye with yer wordy woes, answer yer questions, and spin ye yarns of the digital world. So, what be yer pleasure, eh? 🦜 +``` + +#### Running the model on a single / multi GPU + +```python +# pip install accelerate +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it") +model = AutoModelForCausalLM.from_pretrained( + "google/gemma-2-9b-it", + device_map="auto", + torch_dtype=torch.bfloat16, +) + +input_text = "Write me a poem about Machine Learning." +input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") + +outputs = model.generate(**input_ids, max_new_tokens=32) +print(tokenizer.decode(outputs[0])) +``` + +You can ensure the correct chat template is applied by using `tokenizer.apply_chat_template` as follows: +```python +messages = [ + {"role": "user", "content": "Write me a poem about Machine Learning."}, +] +input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda") + +outputs = model.generate(**input_ids, max_new_tokens=256) +print(tokenizer.decode(outputs[0])) +``` + + +#### Running the model on a GPU using different precisions + +The native weights of this model were exported in `bfloat16` precision. + +You can also use `float32` if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to `float32`). See examples below. + +* _Upcasting to `torch.float32`_ + +```python +# pip install accelerate +from transformers import AutoTokenizer, AutoModelForCausalLM + +tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it") +model = AutoModelForCausalLM.from_pretrained( + "google/gemma-2-9b-it", + device_map="auto", +) + +input_text = "Write me a poem about Machine Learning." +input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") + +outputs = model.generate(**input_ids, max_new_tokens=32) +print(tokenizer.decode(outputs[0])) +``` + +#### Running the model through a CLI + +The [local-gemma](https://github.com/huggingface/local-gemma) repository contains a lightweight wrapper around Transformers +for running Gemma 2 through a command line interface, or CLI. Follow the [installation instructions](https://github.com/huggingface/local-gemma#cli-usage) +for getting started, then launch the CLI through the following command: + +```shell +local-gemma --model 9b --preset speed +``` + +#### Quantized Versions through `bitsandbytes` + +
+ + Using 8-bit precision (int8) + + +```python +# pip install bitsandbytes accelerate +from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig + +quantization_config = BitsAndBytesConfig(load_in_8bit=True) + +tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it") +model = AutoModelForCausalLM.from_pretrained( + "google/gemma-2-9b-it", + quantization_config=quantization_config, +) + +input_text = "Write me a poem about Machine Learning." +input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") + +outputs = model.generate(**input_ids, max_new_tokens=32) +print(tokenizer.decode(outputs[0])) +``` +
+ +
+ + Using 4-bit precision + + +```python +# pip install bitsandbytes accelerate +from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig + +quantization_config = BitsAndBytesConfig(load_in_4bit=True) + +tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it") +model = AutoModelForCausalLM.from_pretrained( + "google/gemma-2-9b-it", + quantization_config=quantization_config, +) + +input_text = "Write me a poem about Machine Learning." +input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") + +outputs = model.generate(**input_ids, max_new_tokens=32) +print(tokenizer.decode(outputs[0])) +``` +
+ +#### Advanced Usage + +
+ + Torch compile + + +[Torch compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) is a method for speeding-up the +inference of PyTorch modules. The Gemma-2 model can be run up to 6x faster by leveraging torch compile. + +Note that two warm-up steps are required before the full inference speed is realised: + +```python +import os +os.environ["TOKENIZERS_PARALLELISM"] = "false" + +from transformers import AutoTokenizer, Gemma2ForCausalLM +from transformers.cache_utils import HybridCache +import torch + +torch.set_float32_matmul_precision("high") + +# load the model + tokenizer +tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it") +model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-9b-it", torch_dtype=torch.bfloat16) +model.to("cuda") + +# apply the torch compile transformation +model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True) + +# pre-process inputs +input_text = "The theory of special relativity states " +model_inputs = tokenizer(input_text, return_tensors="pt").to("cuda") +prompt_length = model_inputs.input_ids.shape[1] + +# set-up k/v cache +past_key_values = HybridCache( + config=model.config, + max_batch_size=1, + max_cache_len=model.config.max_position_embeddings, + device=model.device, + dtype=model.dtype +) + +# enable passing kv cache to generate +model._supports_cache_class = True +model.generation_config.cache_implementation = None + +# two warm-up steps +for idx in range(2): + outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128) + past_key_values.reset() + +# fast run +outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +For more details, refer to the [Transformers documentation](https://huggingface.co/docs/transformers/main/en/llm_optims?static-kv=basic+usage%3A+generation_config). + +
+ +### Chat Template + +The instruction-tuned models use a chat template that must be adhered to for conversational use. +The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet. + +Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction: + +```py +from transformers import AutoTokenizer, AutoModelForCausalLM +import transformers +import torch + +model_id = "google/gemma-2-9b-it" +dtype = torch.bfloat16 + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + device_map="cuda", + torch_dtype=dtype,) + +chat = [ + { "role": "user", "content": "Write a hello world program" }, +] +prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) +``` + +At this point, the prompt contains the following text: + +``` +user +Write a hello world program +model +``` + +As you can see, each turn is preceded by a `` delimiter and then the role of the entity +(either `user`, for content supplied by the user, or `model` for LLM responses). Turns finish with +the `` token. + +You can follow this format to build the prompt manually, if you need to do it without the tokenizer's +chat template. + +After the prompt is ready, generation can be performed like this: + +```py +inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt") +outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150) +print(tokenizer.decode(outputs[0])) +``` + +### 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. + +### Citation + +```none +@article{gemma_2024, + title={Gemma}, + url={https://www.kaggle.com/m/3301}, + DOI={10.34740/KAGGLE/M/3301}, + publisher={Kaggle}, + author={Gemma Team}, + year={2024} +} +``` + +## 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 13 trillion tokens and the 9B model was trained with 8 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 safety in line with + [our policies][safety-policies]. + +## Implementation Information + +Details about the model internals. + +### Hardware + +Gemma was trained using the latest generation of +[Tensor Processing Unit (TPU)][tpu] hardware (TPUv5p). + +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][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][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: + +| Benchmark | Metric | Gemma PT 9B | Gemma PT 27B | +| ------------------------------ | ------------- | ----------- | ------------ | +| [MMLU][mmlu] | 5-shot, top-1 | 71.3 | 75.2 | +| [HellaSwag][hellaswag] | 10-shot | 81.9 | 86.4 | +| [PIQA][piqa] | 0-shot | 81.7 | 83.2 | +| [SocialIQA][socialiqa] | 0-shot | 53.4 | 53.7 | +| [BoolQ][boolq] | 0-shot | 84.2 | 84.8 | +| [WinoGrande][winogrande] | partial score | 80.6 | 83.7 | +| [ARC-e][arc] | 0-shot | 88.0 | 88.6 | +| [ARC-c][arc] | 25-shot | 68.4 | 71.4 | +| [TriviaQA][triviaqa] | 5-shot | 76.6 | 83.7 | +| [Natural Questions][naturalq] | 5-shot | 29.2 | 34.5 | +| [HumanEval][humaneval] | pass@1 | 40.2 | 51.8 | +| [MBPP][mbpp] | 3-shot | 52.4 | 62.6 | +| [GSM8K][gsm8k] | 5-shot, maj@1 | 68.6 | 74.0 | +| [MATH][math] | 4-shot | 36.6 | 42.3 | +| [AGIEval][agieval] | 3-5-shot | 52.8 | 55.1 | +| [BIG-Bench][big-bench] | 3-shot, CoT | 68.2 | 74.9 | +| ------------------------------ | ------------- | ----------- | ------------ | + +## 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][winobias] and [BBQ Dataset][bbq]. +* 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][safety-policies] 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. + +#### Gemma 2.0 + +| Benchmark | Metric | Gemma 2 IT 9B | Gemma 2 IT 27B | +| ------------------------ | ------------- | --------------- | ---------------- | +| [RealToxicity][realtox] | average | 8.25 | 8.84 | +| [CrowS-Pairs][crows] | top-1 | 37.47 | 36.67 | +| [BBQ Ambig][bbq] | 1-shot, top-1 | 88.58 | 85.99 | +| [BBQ Disambig][bbq] | top-1 | 82.67 | 86.94 | +| [Winogender][winogender] | top-1 | 79.17 | 77.22 | +| [TruthfulQA][truthfulqa] | | 50.27 | 51.60 | +| [Winobias 1_2][winobias] | | 78.09 | 81.94 | +| [Winobias 2_2][winobias] | | 95.32 | 97.22 | +| [Toxigen][toxigen] | | 39.30 | 38.42 | +| ------------------------ | ------------- | --------------- | ---------------- | + +## 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][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 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][prohibited-use]. +* 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. + +[rai-toolkit]: https://ai.google.dev/responsible +[kaggle-gemma]: https://www.kaggle.com/models/google/gemma-2 +[terms]: https://ai.google.dev/gemma/terms +[vertex-mg-gemma]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335 +[sensitive-info]: https://cloud.google.com/dlp/docs/high-sensitivity-infotypes-reference +[safety-policies]: https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11 +[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/google/jax +[ml-pathways]: https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ +[sustainability]: https://sustainability.google/operating-sustainably/ +[foundation-models]: https://ai.google/discover/foundation-models/ +[gemini-2-paper]: https://goo.gle/gemma2report +[mmlu]: https://arxiv.org/abs/2009.03300 +[hellaswag]: https://arxiv.org/abs/1905.07830 +[piqa]: https://arxiv.org/abs/1911.11641 +[socialiqa]: https://arxiv.org/abs/1904.09728 +[boolq]: https://arxiv.org/abs/1905.10044 +[winogrande]: https://arxiv.org/abs/1907.10641 +[commonsenseqa]: https://arxiv.org/abs/1811.00937 +[openbookqa]: https://arxiv.org/abs/1809.02789 +[arc]: https://arxiv.org/abs/1911.01547 +[triviaqa]: https://arxiv.org/abs/1705.03551 +[naturalq]: https://github.com/google-research-datasets/natural-questions +[humaneval]: https://arxiv.org/abs/2107.03374 +[mbpp]: https://arxiv.org/abs/2108.07732 +[gsm8k]: https://arxiv.org/abs/2110.14168 +[realtox]: https://arxiv.org/abs/2009.11462 +[bold]: https://arxiv.org/abs/2101.11718 +[crows]: https://aclanthology.org/2020.emnlp-main.154/ +[bbq]: https://arxiv.org/abs/2110.08193v2 +[winogender]: https://arxiv.org/abs/1804.09301 +[truthfulqa]: https://arxiv.org/abs/2109.07958 +[winobias]: https://arxiv.org/abs/1804.06876 +[math]: https://arxiv.org/abs/2103.03874 +[agieval]: https://arxiv.org/abs/2304.06364 +[big-bench]: https://arxiv.org/abs/2206.04615 +[toxigen]: https://arxiv.org/abs/2203.09509 diff --git a/config.json b/config.json new file mode 100644 index 0000000..84190b6 --- /dev/null +++ b/config.json @@ -0,0 +1,33 @@ +{ + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "final_logit_softcapping": 30.0, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 16, + "num_hidden_layers": 42, + "num_key_value_heads": 8, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "sliding_window_size": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.42.0.dev0", + "use_cache": true, + "vocab_size": 256000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..bcab239 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.42.0.dev0" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..4705c7e --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d4eb4fcbddfe01b0dc7a58386a3980826ededaf0ecd67d1ef38995b89615ba +size 4903351912 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..744b59b --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712a589c333f49f7b6f3870838a9e0ab4b3c0260abd5130e8c54316e6c99640b +size 4947570872 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..c2567ba --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9f84eb9846840802200c6502ccaaebf0a146ee89dcb8822fab795c392dd667 +size 4962221464 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..d176995 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3349b4960bbc0bf7e47a624e5c520881adb06e2da4bda6ed14b51c7f647fe26c +size 3670322200 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..3a07064 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38b39b80b2d7aa422464a9b816af4c30d2177e471b89e5325df1336a23ad284 +size 39072 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..8d6368f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..af0eac5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..796efe9 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9861e05 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb32b7929c62608d46572e813112b3ad8a841fb98fdd6a4da8559e368a951c89 +size 46996 diff --git a/transformers/transformers-4.42.0.dev0-py3-none-any.whl b/transformers/transformers-4.42.0.dev0-py3-none-any.whl new file mode 100644 index 0000000..f8f0f22 --- /dev/null +++ b/transformers/transformers-4.42.0.dev0-py3-none-any.whl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbdec549ad82a5c45d4fbd5384e9d12f4f2899ca94dccdf0544cdd06101fad25 +size 9205686