Commit
•
09c8264
1
Parent(s):
fbabb56
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,88 +1,88 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: google/gemma-2-27b-it
|
| 3 |
-
inference: false
|
| 4 |
-
license: gemma
|
| 5 |
-
library_name: transformers
|
| 6 |
-
pipeline_tag: text-generation
|
| 7 |
-
model_creator: Google
|
| 8 |
-
model_name: gemma-2-27b-it
|
| 9 |
-
quantized_by: Second State Inc.
|
| 10 |
-
tags:
|
| 11 |
-
- conversational
|
| 12 |
-
---
|
| 13 |
-
|
| 14 |
-
<!-- header start -->
|
| 15 |
-
<!-- 200823 -->
|
| 16 |
-
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 17 |
-
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 18 |
-
</div>
|
| 19 |
-
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
| 20 |
-
<!-- header end -->
|
| 21 |
-
|
| 22 |
-
# Gemma-2-27b-it-GGUF
|
| 23 |
-
|
| 24 |
-
## Original Model
|
| 25 |
-
|
| 26 |
-
[google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)
|
| 27 |
-
|
| 28 |
-
## Run with LlamaEdge
|
| 29 |
-
|
| 30 |
-
<!-- - LlamaEdge version: [v0.8.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.1) and above -->
|
| 31 |
-
|
| 32 |
-
- LlamaEdge version: coming soon
|
| 33 |
-
|
| 34 |
-
- Prompt template
|
| 35 |
-
|
| 36 |
-
- Prompt type: `gemma-instruct`
|
| 37 |
-
|
| 38 |
-
- Prompt string
|
| 39 |
-
|
| 40 |
-
```text
|
| 41 |
-
<bos><start_of_turn>user
|
| 42 |
-
{user_message}<end_of_turn>
|
| 43 |
-
<start_of_turn>model
|
| 44 |
-
{model_message}<end_of_turn>model
|
| 45 |
-
```
|
| 46 |
-
|
| 47 |
-
- Context size: `8192`
|
| 48 |
-
|
| 49 |
-
- Run as LlamaEdge service
|
| 50 |
-
|
| 51 |
-
```bash
|
| 52 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-2-27b-it-Q5_K_M.gguf \
|
| 53 |
-
llama-api-server.wasm \
|
| 54 |
-
--prompt-template gemma-instruct \
|
| 55 |
-
--ctx-size 8192 \
|
| 56 |
-
--model-name gemma-2-9b
|
| 57 |
-
```
|
| 58 |
-
|
| 59 |
-
- Run as LlamaEdge command app
|
| 60 |
-
|
| 61 |
-
```bash
|
| 62 |
-
wasmedge --dir .:. \
|
| 63 |
-
--nn-preload default:GGML:AUTO:gemma-2-27b-it-Q5_K_M.gguf \
|
| 64 |
-
llama-chat.wasm \
|
| 65 |
-
--prompt-template gemma-instruct \
|
| 66 |
-
--ctx-size 8192
|
| 67 |
-
```
|
| 68 |
-
|
| 69 |
-
## Quantized GGUF Models
|
| 70 |
-
|
| 71 |
-
| Name | Quant method | Bits | Size | Use case |
|
| 72 |
-
| ---- | ---- | ---- | ---- | ----- |
|
| 73 |
-
| [gemma-2-27b-it-Q2_K.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q2_K.gguf) | Q2_K | 2 | 10.4 GB| smallest, significant quality loss - not recommended for most purposes |
|
| 74 |
-
| [gemma-2-27b-it-Q3_K_L.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_L.gguf) | Q3_K_L | 3 | 14.5 GB| small, substantial quality loss |
|
| 75 |
-
| [gemma-2-27b-it-Q3_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_M.gguf) | Q3_K_M | 3 | 13.4 GB| very small, high quality loss |
|
| 76 |
-
| [gemma-2-27b-it-Q3_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_S.gguf) | Q3_K_S | 3 | 12.2 GB| very small, high quality loss |
|
| 77 |
-
| [gemma-2-27b-it-Q4_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_0.gguf) | Q4_0 | 4 | 15.6 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 78 |
-
| [gemma-2-27b-it-Q4_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_K_M.gguf) | Q4_K_M | 4 | 16.6 GB| medium, balanced quality - recommended |
|
| 79 |
-
| [gemma-2-27b-it-Q4_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_K_S.gguf) | Q4_K_S | 4 | 15.7 GB| small, greater quality loss |
|
| 80 |
-
| [gemma-2-27b-it-Q5_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_0.gguf) | Q5_0 | 5 | 18.9 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 81 |
-
| [gemma-2-27b-it-Q5_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_K_M.gguf) | Q5_K_M | 5 | 19.4 GB| large, very low quality loss - recommended |
|
| 82 |
-
| [gemma-2-27b-it-Q5_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_K_S.gguf) | Q5_K_S | 5 | 18.9 GB| large, low quality loss - recommended |
|
| 83 |
-
| [gemma-2-27b-it-Q6_K.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q6_K.gguf) | Q6_K | 6 | 22.3 GB| very large, extremely low quality loss |
|
| 84 |
-
| [gemma-2-27b-it-Q8_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q8_0.gguf) | Q8_0 | 8 | 28.9 GB| very large, extremely low quality loss - not recommended |
|
| 85 |
-
| [gemma-2-27b-it-f16-00001-of-00002.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-f16-00001-of-00002.gguf) | f16 | 16 | 29.9 GB| |
|
| 86 |
-
| [gemma-2-27b-it-f16-00002-of-00002.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-f16-00002-of-00002.gguf) | f16 | 16 | 24.6 GB| |
|
| 87 |
-
|
| 88 |
-
*Quantized with llama.cpp
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-2-27b-it
|
| 3 |
+
inference: false
|
| 4 |
+
license: gemma
|
| 5 |
+
library_name: transformers
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
model_creator: Google
|
| 8 |
+
model_name: gemma-2-27b-it
|
| 9 |
+
quantized_by: Second State Inc.
|
| 10 |
+
tags:
|
| 11 |
+
- conversational
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- header start -->
|
| 15 |
+
<!-- 200823 -->
|
| 16 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 17 |
+
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 18 |
+
</div>
|
| 19 |
+
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
| 20 |
+
<!-- header end -->
|
| 21 |
+
|
| 22 |
+
# Gemma-2-27b-it-GGUF
|
| 23 |
+
|
| 24 |
+
## Original Model
|
| 25 |
+
|
| 26 |
+
[google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)
|
| 27 |
+
|
| 28 |
+
## Run with LlamaEdge
|
| 29 |
+
|
| 30 |
+
<!-- - LlamaEdge version: [v0.8.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.1) and above -->
|
| 31 |
+
|
| 32 |
+
- LlamaEdge version: coming soon
|
| 33 |
+
|
| 34 |
+
- Prompt template
|
| 35 |
+
|
| 36 |
+
- Prompt type: `gemma-instruct`
|
| 37 |
+
|
| 38 |
+
- Prompt string
|
| 39 |
+
|
| 40 |
+
```text
|
| 41 |
+
<bos><start_of_turn>user
|
| 42 |
+
{user_message}<end_of_turn>
|
| 43 |
+
<start_of_turn>model
|
| 44 |
+
{model_message}<end_of_turn>model
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
- Context size: `8192`
|
| 48 |
+
|
| 49 |
+
- Run as LlamaEdge service
|
| 50 |
+
|
| 51 |
+
```bash
|
| 52 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-2-27b-it-Q5_K_M.gguf \
|
| 53 |
+
llama-api-server.wasm \
|
| 54 |
+
--prompt-template gemma-instruct \
|
| 55 |
+
--ctx-size 8192 \
|
| 56 |
+
--model-name gemma-2-9b
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
- Run as LlamaEdge command app
|
| 60 |
+
|
| 61 |
+
```bash
|
| 62 |
+
wasmedge --dir .:. \
|
| 63 |
+
--nn-preload default:GGML:AUTO:gemma-2-27b-it-Q5_K_M.gguf \
|
| 64 |
+
llama-chat.wasm \
|
| 65 |
+
--prompt-template gemma-instruct \
|
| 66 |
+
--ctx-size 8192
|
| 67 |
+
```
|
| 68 |
+
|
| 69 |
+
## Quantized GGUF Models
|
| 70 |
+
|
| 71 |
+
| Name | Quant method | Bits | Size | Use case |
|
| 72 |
+
| ---- | ---- | ---- | ---- | ----- |
|
| 73 |
+
| [gemma-2-27b-it-Q2_K.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q2_K.gguf) | Q2_K | 2 | 10.4 GB| smallest, significant quality loss - not recommended for most purposes |
|
| 74 |
+
| [gemma-2-27b-it-Q3_K_L.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_L.gguf) | Q3_K_L | 3 | 14.5 GB| small, substantial quality loss |
|
| 75 |
+
| [gemma-2-27b-it-Q3_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_M.gguf) | Q3_K_M | 3 | 13.4 GB| very small, high quality loss |
|
| 76 |
+
| [gemma-2-27b-it-Q3_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_S.gguf) | Q3_K_S | 3 | 12.2 GB| very small, high quality loss |
|
| 77 |
+
| [gemma-2-27b-it-Q4_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_0.gguf) | Q4_0 | 4 | 15.6 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 78 |
+
| [gemma-2-27b-it-Q4_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_K_M.gguf) | Q4_K_M | 4 | 16.6 GB| medium, balanced quality - recommended |
|
| 79 |
+
| [gemma-2-27b-it-Q4_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_K_S.gguf) | Q4_K_S | 4 | 15.7 GB| small, greater quality loss |
|
| 80 |
+
| [gemma-2-27b-it-Q5_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_0.gguf) | Q5_0 | 5 | 18.9 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 81 |
+
| [gemma-2-27b-it-Q5_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_K_M.gguf) | Q5_K_M | 5 | 19.4 GB| large, very low quality loss - recommended |
|
| 82 |
+
| [gemma-2-27b-it-Q5_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_K_S.gguf) | Q5_K_S | 5 | 18.9 GB| large, low quality loss - recommended |
|
| 83 |
+
| [gemma-2-27b-it-Q6_K.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q6_K.gguf) | Q6_K | 6 | 22.3 GB| very large, extremely low quality loss |
|
| 84 |
+
| [gemma-2-27b-it-Q8_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q8_0.gguf) | Q8_0 | 8 | 28.9 GB| very large, extremely low quality loss - not recommended |
|
| 85 |
+
| [gemma-2-27b-it-f16-00001-of-00002.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-f16-00001-of-00002.gguf) | f16 | 16 | 29.9 GB| |
|
| 86 |
+
| [gemma-2-27b-it-f16-00002-of-00002.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-f16-00002-of-00002.gguf) | f16 | 16 | 24.6 GB| |
|
| 87 |
+
|
| 88 |
+
*Quantized with llama.cpp b3259*
|