92 lines
4.5 KiB
Markdown
92 lines
4.5 KiB
Markdown
---
|
||
base_model: google/gemma-2-9b
|
||
library_name: transformers
|
||
license: gemma
|
||
pipeline_tag: text-generation
|
||
tags:
|
||
- conversational
|
||
quantized_by: fedric95
|
||
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
|
||
---
|
||
|
||
## Llamacpp Quantizations of Meta-Llama-3.1-8B
|
||
|
||
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3583">b3583</a> for quantization.
|
||
|
||
Original model: https://huggingface.co/google/gemma-2-9b
|
||
|
||
## Download a file (not the whole branch) from below:
|
||
|
||
| Filename | Quant type | File Size | Perplexity (wikitext-2-raw-v1.test) |
|
||
| -------- | ---------- | --------- | ----------- |
|
||
| [gemma-2-9b.FP32.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b.FP32.gguf) | FP32 | 37.00GB | 6.9209 +/- 0.04660 |
|
||
| [gemma-2-9b-Q8_0.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q8_0.gguf) | Q8_0 | 9.83GB | 6.9222 +/- 0.04660 |
|
||
| [gemma-2-9b-Q6_K.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q6_K.gguf) | Q6_K | 7.59GB | 6.9353 +/- 0.04675 |
|
||
| [gemma-2-9b-Q5_K_M.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q5_K_M.gguf) | Q5_K_M | 6.65GB | 6.9571 +/- 0.04687 |
|
||
| [gemma-2-9b-Q5_K_S.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q5_K_S.gguf) | Q5_K_S | 6.48GB | 6.9623 +/- 0.04690 |
|
||
| [gemma-2-9b-Q4_K_M.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q4_K_M.gguf) | Q4_K_M | 5.76GB | 7.0220 +/- 0.04737 |
|
||
| [gemma-2-9b-Q4_K_S.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q4_K_S.gguf) | Q4_K_S | 5.48GB | 7.0622 +/- 0.04777 |
|
||
| [gemma-2-9b-Q3_K_L.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q3_K_L.gguf) | Q3_K_L | 5.13GB | 7.2144 +/- 0.04910 |
|
||
| [gemma-2-9b-Q3_K_M.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q3_K_M.gguf) | Q3_K_M | 4.76GB | 7.2849 +/- 0.04970 |
|
||
| [gemma-2-9b-Q3_K_S.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q3_K_S.gguf) | Q3_K_S | 4.34GB | 7.6869 +/- 0.05373 |
|
||
| [gemma-2-9b-Q2_K.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q2_K.gguf) | Q2_K | 3.81GB | 8.7979 +/- 0.06191 |
|
||
|
||
## Benchmark Results
|
||
|
||
Results have been computed using:
|
||
|
||
[hellaswage_val_full](https://raw.githubusercontent.com/klosax/hellaswag_text_data/main/hellaswag_val_full.txt)
|
||
|
||
[winogrande-debiased-eval](https://huggingface.co/datasets/ikawrakow/winogrande-eval-for-llama.cpp/raw/main/winogrande-debiased-eval.csv)
|
||
|
||
[mmlu-validation](https://huggingface.co/datasets/ikawrakow/validation-datasets-for-llama.cpp/resolve/main/mmlu-validation.bin)
|
||
|
||
| Benchmark | Quant type | Metric |
|
||
| -------- | ---------- | --------- |
|
||
| WinoGrande (0-shot) | Q8_0 | 74.4278 +/- 1.2261 |
|
||
| WinoGrande (0-shot) | Q4_K_M | 74.8224 +/- 1.2198 |
|
||
| WinoGrande (0-shot) | Q3_K_M | 74.1910 +/- 1.2298 |
|
||
| WinoGrande (0-shot) | Q3_K_S | 72.6125 +/- 1.2533 |
|
||
| WinoGrande (0-shot) | Q2_K | 71.4286 +/- 1.2697 |
|
||
| HellaSwag (0-shot) | Q8_0 | 78.39075881 |
|
||
| HellaSwag (0-shot) | Q4_K_M | 77.87293368 |
|
||
| HellaSwag (0-shot) | Q3_K_M | 76.64807807 |
|
||
| HellaSwag (0-shot) | Q3_K_S | 76.08046206 |
|
||
| HellaSwag (0-shot) | Q2_K | 73.07309301 |
|
||
| MMLU (0-shot) | Q8_0 | 42.5065 +/- 1.2569 |
|
||
| MMLU (0-shot) | Q4_K_M | 42.5065 +/- 1.2569 |
|
||
| MMLU (0-shot) | Q3_K_M | 41.3437 +/- 1.2520 |
|
||
| MMLU (0-shot) | Q3_K_S | 40.5685 +/- 1.2484 |
|
||
| MMLU (0-shot) | Q2_K | 38.1137 +/- 1.2348 |
|
||
|
||
## Downloading using huggingface-cli
|
||
|
||
First, make sure you have hugginface-cli installed:
|
||
|
||
```
|
||
pip install -U "huggingface_hub[cli]"
|
||
```
|
||
|
||
Then, you can target the specific file you want:
|
||
|
||
```
|
||
huggingface-cli download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q4_K_M.gguf" --local-dir ./
|
||
```
|
||
|
||
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
|
||
|
||
```
|
||
huggingface-cli download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q8_0.gguf/*" --local-dir gemma-2-9b-Q8_0
|
||
```
|
||
|
||
You can either specify a new local-dir (gemma-2-9b-Q8_0) or download them all in place (./)
|
||
|
||
|
||
## Reproducibility
|
||
|
||
https://github.com/ggerganov/llama.cpp/discussions/9020#discussioncomment-10335638
|