|
--- |
|
base_model: google/gemma-1.1-7b-it |
|
inference: false |
|
library_name: transformers |
|
license: gemma |
|
model_creator: Google |
|
model_name: Gemma 1.1 7B (IT) |
|
quantized_by: Second State Inc. |
|
--- |
|
|
|
<!-- header start --> |
|
<!-- 200823 --> |
|
<div style="width: auto; margin-left: auto; margin-right: auto"> |
|
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;"> |
|
</div> |
|
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> |
|
<!-- header end --> |
|
|
|
# Gemma-1.1-7b-it-GGUF |
|
|
|
## Original Model |
|
|
|
[google/gemma-1.1-7b-it](https://huggingface.co/google/gemma-1.1-7b-it) |
|
|
|
## Run with LlamaEdge |
|
|
|
- LlamaEdge version: [v0.8.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.1) and above |
|
|
|
- Prompt template |
|
|
|
- Prompt type: `gemma-instruct` |
|
|
|
- Prompt string |
|
|
|
```text |
|
<bos><start_of_turn>user |
|
{user_message}<end_of_turn> |
|
<start_of_turn>model |
|
{model_message}<end_of_turn>model |
|
``` |
|
|
|
- Context size: `3072` |
|
|
|
- Run as LlamaEdge service |
|
|
|
```bash |
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-1.1-7b-it-Q5_K_M.gguf \ |
|
llama-api-server.wasm \ |
|
--prompt-template gemma-instruct \ |
|
--ctx-size 3072 \ |
|
--model-name gemma-1.1-7b |
|
``` |
|
|
|
- Run as LlamaEdge command app |
|
|
|
```bash |
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-1.1-7b-it-Q5_K_M.gguf llama-chat.wasm -p gemma-instruct -c 3072 |
|
``` |
|
|
|
## Quantized GGUF Models |
|
|
|
| Name | Quant method | Bits | Size | Use case | |
|
| ---- | ---- | ---- | ---- | ----- | |
|
| [gemma-1.1-7b-it-Q2_K.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q2_K.gguf) | Q2_K | 2 | 3.48 GB| smallest, significant quality loss - not recommended for most purposes | |
|
| [gemma-1.1-7b-it-Q3_K_L.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q3_K_L.gguf) | Q3_K_L | 3 | 4.71 GB| small, substantial quality loss | |
|
| [gemma-1.1-7b-it-Q3_K_M.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q3_K_M.gguf) | Q3_K_M | 3 | 4.37 GB| very small, high quality loss | |
|
| [gemma-1.1-7b-it-Q3_K_S.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q3_K_S.gguf) | Q3_K_S | 3 | 3.98 GB| very small, high quality loss | |
|
| [gemma-1.1-7b-it-Q4_0.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q4_0.gguf) | Q4_0 | 4 | 5.01 GB| legacy; small, very high quality loss - prefer using Q3_K_M | |
|
| [gemma-1.1-7b-it-Q4_K_M.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q4_K_M.gguf) | Q4_K_M | 4 | 5.33 GB| medium, balanced quality - recommended | |
|
| [gemma-1.1-7b-it-Q4_K_S.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q4_K_S.gguf) | Q4_K_S | 4 | 5.05 GB| small, greater quality loss | |
|
| [gemma-1.1-7b-it-Q5_0.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q5_0.gguf) | Q5_0 | 5 | 5.98 GB| legacy; medium, balanced quality - prefer using Q4_K_M | |
|
| [gemma-1.1-7b-it-Q5_K_M.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q5_K_M.gguf) | Q5_K_M | 5 | 6.14 GB| large, very low quality loss - recommended | |
|
| [gemma-1.1-7b-it-Q5_K_S.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q5_K_S.gguf) | Q5_K_S | 5 | 5.98 GB| large, low quality loss - recommended | |
|
| [gemma-1.1-7b-it-Q6_K.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q6_K.gguf) | Q6_K | 6 | 7.01 GB| very large, extremely low quality loss | |
|
| [gemma-1.1-7b-it-Q8_0.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q8_0.gguf) | Q8_0 | 8 | 9.08 GB| very large, extremely low quality loss - not recommended | |
|
| [gemma-1.1-7b-it-f16.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-f16.gguf) | f16 | 16 | 17.1 GB| | |
|
|
|
*Quantized with llama.cpp b2589* |
