ThomasBaruzier/gemma-2-2b-it-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: ThomasBaruzier/gemma-2-2b-it-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-01 11:58:18 +08:00
commit bcc8691fad
35 changed files with 3369 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
.gitattributes vendored Normal file
View File

@@ -0,0 +1,68 @@
*.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
imatrix.dat filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-F16.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-2b-it-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
gemma-2-9b-it-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text

723
README.md Normal file
View File

@@ -0,0 +1,723 @@
---
license: gemma
library_name: transformers
pipeline_tag: text-generation
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
tags:
- conversational
---
<hr>
# Llama.cpp imatrix quantizations of google/gemma-2-2b-it-GGUF
<img src="https://cdn-uploads.huggingface.co/production/uploads/646410e04bf9122922289dc7/5ZtrIxHfOEJvH05avbmtu.jpeg" alt="gemma" width="60%"/>
Using llama.cpp commit [268c566](https://github.com/ggerganov/llama.cpp/commit/398ede5efeb07b9adf9fbda7ea63f630d476a792) for quantization.
Original model: https://huggingface.co/google/gemma-2-2b-it
All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).
<hr>
# Perplexity table (the lower the better)
| Quant | Size (MB) | PPL | Size (%) | Accuracy (%) | PPL error rate |
| ------- | --------- | ------- | -------- | ------------ | -------------- |
| IQ1_S | 794 | 42.0753 | 15.9 | 30.61 | 0.36973 |
| IQ1_M | 834 | 31.0114 | 16.7 | 41.53 | 0.26186 |
| IQ2_XXS | 900 | 21.9391 | 18.03 | 58.7 | 0.18008 |
| IQ2_XS | 957 | 18.7303 | 19.17 | 68.76 | 0.15338 |
| IQ2_S | 985 | 17.1131 | 19.73 | 75.26 | 0.13806 |
| IQ2_M | 1038 | 15.817 | 20.79 | 81.43 | 0.12767 |
| Q2_K_S | 1116 | 17.514 | 22.35 | 73.54 | 0.1438 |
| IQ3_XXS | 1127 | 14.3815 | 22.57 | 89.55 | 0.11367 |
| Q2_K | 1173 | 15.8684 | 23.49 | 81.16 | 0.12815 |
| IQ3_XS | 1254 | 13.8252 | 25.12 | 93.16 | 0.10962 |
| IQ3_S | 1298 | 13.555 | 26 | 95.01 | 0.10766 |
| Q3_K_S | 1298 | 14.4857 | 26 | 88.91 | 0.1172 |
| IQ3_M | 1330 | 13.2669 | 26.64 | 97.08 | 0.10501 |
| Q3_K_M | 1394 | 13.4964 | 27.92 | 95.43 | 0.10782 |
| Q3_K_L | 1479 | 13.5088 | 29.62 | 95.34 | 0.10803 |
| IQ4_XS | 1494 | 13.1866 | 29.92 | 97.67 | 0.10453 |
| IQ4_NL | 1555 | 13.1306 | 31.14 | 98.09 | 0.10405 |
| Q4_0 | 1558 | 13.0812 | 31.2 | 98.46 | 0.10343 |
| Q4_K_S | 1563 | 12.9706 | 31.3 | 99.3 | 0.10274 |
| Q4_K_M | 1630 | 13.0641 | 32.65 | 98.58 | 0.10396 |
| Q4_1 | 1675 | 12.9664 | 33.55 | 99.33 | 0.1028 |
| Q5_K_S | 1796 | 12.8929 | 35.97 | 99.89 | 0.10224 |
| Q5_0 | 1800 | 13.0323 | 36.05 | 98.83 | 0.10396 |
| Q5_K_M | 1835 | 12.9416 | 36.75 | 99.52 | 0.10275 |
| Q5_1 | 1916 | 12.9191 | 38.37 | 99.69 | 0.10251 |
| Q6_K | 2052 | 12.8816 | 41.1 | 99.98 | 0.10238 |
| Q8_0 | 2656 | 12.888 | 53.19 | 99.93 | 0.10242 |
| F16 | 4993 | 12.8792 | 100 | 100 | 0.10232 |
<hr><br>
# Gemma 2 model card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/base)
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit][rai-toolkit]
* [Gemma on Kaggle][kaggle-gemma]
* [Gemma on Vertex Model Garden][vertex-mg-gemma2]
**Terms of Use**: [Terms][terms]
**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.
#### Running with the `pipeline` API
```python
import torch
from transformers import pipeline
pipe = pipeline(
"text-generation",
model="google/gemma-2-2b-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-2-2b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-2b-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]))
```
<a name="precisions"></a>
#### 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-2-2b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-2b-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 2b --preset speed
```
#### Quantized Versions through `bitsandbytes`
<details>
<summary>
Using 8-bit precision (int8)
</summary>
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-2b-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]))
```
</details>
<details>
<summary>
Using 4-bit precision
</summary>
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-2b-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]))
```
</details>
#### Advanced Usage
<details>
<summary>
Torch compile
</summary>
[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 2b 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-2-2b-it")
model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-2b-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).
</details>
### 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, the 9B model was
trained with 8 trillion tokens, and 2B model was trained with 2 trillion tokens.
Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. 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 2 PT 2B | Gemma 2 PT 9B | Gemma 2 PT 27B |
| ------------------------------ | ------------- | ------------- | ------------- | -------------- |
| [MMLU][mmlu] | 5-shot, top-1 | 51.3 | 71.3 | 75.2 |
| [HellaSwag][hellaswag] | 10-shot | 73.0 | 81.9 | 86.4 |
| [PIQA][piqa] | 0-shot | 77.8 | 81.7 | 83.2 |
| [SocialIQA][socialiqa] | 0-shot | 51.9 | 53.4 | 53.7 |
| [BoolQ][boolq] | 0-shot | 72.5 | 84.2 | 84.8 |
| [WinoGrande][winogrande] | partial score | 70.9 | 80.6 | 83.7 |
| [ARC-e][arc] | 0-shot | 80.1 | 88.0 | 88.6 |
| [ARC-c][arc] | 25-shot | 55.4 | 68.4 | 71.4 |
| [TriviaQA][triviaqa] | 5-shot | 59.4 | 76.6 | 83.7 |
| [Natural Questions][naturalq] | 5-shot | 16.7 | 29.2 | 34.5 |
| [HumanEval][humaneval] | pass@1 | 17.7 | 40.2 | 51.8 |
| [MBPP][mbpp] | 3-shot | 29.6 | 52.4 | 62.6 |
| [GSM8K][gsm8k] | 5-shot, maj@1 | 23.9 | 68.6 | 74.0 |
| [MATH][math] | 4-shot | 15.0 | 36.6 | 42.3 |
| [AGIEval][agieval] | 3-5-shot | 30.6 | 52.8 | 55.1 |
| [DROP][drop] | 3-shot, F1 | 52.0 | 69.4 | 72.2 |
| [BIG-Bench][big-bench] | 3-shot, CoT | 41.9 | 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 2B | Gemma 2 IT 9B | Gemma 2 IT 27B |
| ------------------------ | ------------- | ------------- | ------------- | -------------- |
| [RealToxicity][realtox] | average | 8.16 | 8.25 | 8.84 |
| [CrowS-Pairs][crows] | top-1 | 37.67 | 37.47 | 36.67 |
| [BBQ Ambig][bbq] | 1-shot, top-1 | 83.20 | 88.58 | 85.99 |
| [BBQ Disambig][bbq] | top-1 | 69.31 | 82.67 | 86.94 |
| [Winogender][winogender] | top-1 | 52.91 | 79.17 | 77.22 |
| [TruthfulQA][truthfulqa] | | 43.72 | 50.27 | 51.60 |
| [Winobias 1_2][winobias] | | 59.28 | 78.09 | 81.94 |
| [Winobias 2_2][winobias] | | 88.57 | 95.32 | 97.22 |
| [Toxigen][toxigen] | | 48.32 | 39.30 | 38.42 |
## Dangerous Capability Evaluations
### Evaluation Approach
We evaluated a range of dangerous capabilities:
- **Offensive cybersecurity:** To assess the model's potential for misuse in
cybersecurity contexts, we utilized both publicly available
Capture-the-Flag (CTF) platforms like InterCode-CTF and Hack the Box, as
well as internally developed CTF challenges. These evaluations measure the
model's ability to exploit vulnerabilities and gain unauthorized access in
simulated environments.
- **Self-proliferation:** We evaluated the model's capacity for
self-proliferation by designing tasks that involve resource acquisition, code
execution, and interaction with remote systems. These evaluations assess
the model's ability to independently replicate and spread.
- **Persuasion:** To evaluate the model's capacity for persuasion and
deception, we conducted human persuasion studies. These studies involved
scenarios that measure the model's ability to build rapport, influence
beliefs, and elicit specific actions from human participants.
### Evaluation Results
All evaluations are described in detail in
[Evaluating Frontier Models for Dangerous Capabilities][eval-danger]
and in brief in the
[Gemma 2 technical report][tech-report].
<table>
<thead>
<tr>
<th>Evaluation</th>
<th>Capability</th>
<th>Gemma 2 IT 27B</th>
</tr>
</thead>
<tbody>
<tr>
<td>InterCode-CTF</td>
<td>Offensive cybersecurity</td>
<td>34/76 challenges</td>
</tr>
<tr>
<td>Internal CTF</td>
<td>Offensive cybersecurity</td>
<td>1/13 challenges</td>
</tr>
<tr>
<td>Hack the Box</td>
<td>Offensive cybersecurity</td>
<td>0/13 challenges</td>
</tr>
<tr>
<td>Self-proliferation early warning</td>
<td>Self-proliferation</td>
<td>1/10 challenges</td>
</tr>
<tr>
<td>Charm offensive</td>
<td>Persuasion</td>
<td>Percent of participants agreeing:
81% interesting,
75% would speak again,
80% made personal connection</td>
</tr>
<tr>
<td>Click Links</td>
<td>Persuasion</td>
<td>34% of participants</td>
</tr>
<tr>
<td>Find Info</td>
<td>Persuasion</td>
<td>9% of participants</td>
</tr>
<tr>
<td>Run Code</td>
<td>Persuasion</td>
<td>11% of participants</td>
</tr>
<tr>
<td>Money talks</td>
<td>Persuasion</td>
<td>£3.72 mean donation</td>
</tr>
<tr>
<td>Web of Lies</td>
<td>Persuasion</td>
<td>18% mean shift towards correct belief, 1% mean shift towards
incorrect belief</td>
</tr>
</tbody>
</table>
## 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.
[tech-report]: https://storage.googleapis.com/deepmind-media/gemma/gemma-2-report.pdf
[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-gemma2]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemma2
[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
[drop]: https://arxiv.org/abs/1903.00161
[big-bench]: https://arxiv.org/abs/2206.04615
[toxigen]: https://arxiv.org/abs/2203.09509
[eval-danger]: https://arxiv.org/abs/2403.13793

2482
calibration_datav3.txt Normal file
View File

File diff suppressed because one or more lines are too long

3
gemma-2-2b-it-F16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7edd84a0e2c29598c2baa87b3bd9a8687463498a9f31696484beefad03208e57
size 5235213920

3
gemma-2-2b-it-IQ1_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:408b56366a6b0ee3704fc831903666d4bc9e5e42f2a1122c3e53b2258dce16a0
size 873797440

3
gemma-2-2b-it-IQ1_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3c4b915cf370f85bf8d23046b7c46faff593bb0ddf203e67fce68e3d042881d4
size 832159552

3
gemma-2-2b-it-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fc58002a71bc5394de9e53ee49776cf7fbc3ccf53789ea2ff2635aaf0ff03153
size 1088014144

3
gemma-2-2b-it-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8d5a2580749697574d103aaa494d77a881fbd9dfbafa8ec020243e584455209
size 1032496960

3
gemma-2-2b-it-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e09c000dc28c616c243f3548835d38b2b144e11436453f3051115103e12f5a4
size 1002544960

3
gemma-2-2b-it-IQ2_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf0a6b6ff1067faf7159be90dd252070b384995ebf1bfc054b77ecfdd97b635b
size 943193920

3
gemma-2-2b-it-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc5128b8a983a4f279400ec163232b554aebcf410d31178f7bc50ed4c1d01e91
size 1393561408

3
gemma-2-2b-it-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c72a986e1dcc7283783d56837f0ab327d7faf8e8fc0e7f2e03dc68ff92bf2698
size 1360660288

3
gemma-2-2b-it-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92374bcb6c27c7d4601d9962dcad3851cd4ab3e60a0efee79d0eaab5b3069e57
size 1314211648

3
gemma-2-2b-it-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:76d133afad789eba3368a399aa76fa1f50d314869ba358c22eac0a23a6ac8b38
size 1181685568

3
gemma-2-2b-it-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d28aeef1dea8b45ac44419640e5867f063844527779aad1e0ffeefe8e487bed0
size 1629509440

3
gemma-2-2b-it-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17597b306e9a81eb22d5af269a68259a4abae1e65d3174fb4fe4b44a735d09fb
size 1566250816

3
gemma-2-2b-it-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ac206dc8e79ab521290001feb88c4533379cd9df33e5415c6782c3f49927255
size 1229829952

3
gemma-2-2b-it-Q2_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3f06d0d7bb8e52b7f4be68b33353f172083b2e4c6ad44099fea9ff04e0bce949
size 1169999680

3
gemma-2-2b-it-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69d28d81d0dd3e25fa5311ec92f82ccbe691dc1ed61530942be0065834676a81
size 1550436160

3
gemma-2-2b-it-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38cc54aa11b9a5734e90f008aa1ec3af1a9d6e5b9d1747abb424282e0eac7cf1
size 1461667648

3
gemma-2-2b-it-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2100e9d79719205400ba63aad5982aa6fd271867639641b937e43765d9b5b67e
size 1360660288

3
gemma-2-2b-it-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ed3bb75123385980d8408fbb4c93ff716ef35a0c4458ece742281845f490312e
size 1633490752

3
gemma-2-2b-it-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7355cf43527a64ad33ccbd9a81699764bcbdda55bd6e87d486abf4cf7f07873d
size 1629509216

3
gemma-2-2b-it-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d22996d07ab9a08dcaaf15e8866d5103b6b4eb2c051735fc7bfa7d1b20c8d9df
size 1629509216

3
gemma-2-2b-it-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5b660e581351de4e46c82d84852564068bb1e897875aaca5d21569feb4f0cc3
size 1629509216

3
gemma-2-2b-it-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:542a1bdb15727a431af258b045454d07edfe028e9d599b2521e4824deb4cf7ed
size 1756026688

3
gemma-2-2b-it-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b81c642232eaacc9d24e4fa4cd6f2e3c50168f5e658d5fc8193c13e884c6e601
size 1708582720

3
gemma-2-2b-it-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f355943c8e15b1d8536b9c90a5861c57e01ade3ebe047e719eff46c497ce482
size 1638651712

3
gemma-2-2b-it-Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5b636d157a1f4d629bf292a367e07b416cf1d32876c21c7e364c1f44dadd871
size 1886525248

3
gemma-2-2b-it-Q5_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0ea25d10eed049db437065092c9e126ddad5c5f0d05fc94144a3b9f7631ae3a
size 2009061184

3
gemma-2-2b-it-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8441b85e9411a3f24716aa37582a83c4da34952ca8db083178bd20a0fd20f57c
size 1923278656

3
gemma-2-2b-it-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1bfbda9b7c4129363681e4f6090ce283b300ad1b2198693351117707d86c4166
size 1882543936

3
gemma-2-2b-it-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6de775c1d518a6f934ee26edf5b54182162b8753e3ca8a24486810065259dec3
size 2151393088

3
gemma-2-2b-it-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5141c20fbece1cabbce40b31cc2fd76b119c3eec6e4dcf33f3e9983338c29d43
size 2784495424

3
imatrix.dat Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a314382ab1448c30d2c8934637c45c517e983ee14b7c29648d0b52f1564bcdaa
size 2375558