Xin Liu
commited on
Commit
·
852077c
1
Parent(s):
3b6697a
Update
Browse filesSigned-off-by: Xin Liu <sam@secondstate.io>
README.md
CHANGED
|
@@ -1,7 +1,74 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ehartford/Wizard-Vicuna-13B-Uncensored
|
| 3 |
+
inference: false
|
| 4 |
+
library_name: transformers
|
| 5 |
+
license: other
|
| 6 |
+
model_creator: Eric Hartford
|
| 7 |
+
model_name: Wizard Vicuna 13B Uncensored
|
| 8 |
+
model_type: llama
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
quantized_by: Second State Inc.
|
| 11 |
+
language:
|
| 12 |
+
- en
|
| 13 |
+
tags:
|
| 14 |
+
- uncensored
|
| 15 |
+
datasets:
|
| 16 |
+
- ehartford/wizard_vicuna_70k_unfiltered
|
| 17 |
+
---
|
| 18 |
|
| 19 |
+
<!-- header start -->
|
| 20 |
+
<!-- 200823 -->
|
| 21 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 22 |
+
<img src="https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 23 |
+
</div>
|
| 24 |
+
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
| 25 |
+
<!-- header end -->
|
| 26 |
|
| 27 |
+
# Wizard-Vicuna-13B-Uncensored-GGUF
|
| 28 |
+
|
| 29 |
+
## Original Model
|
| 30 |
+
|
| 31 |
+
[cognitivecomputations/Wizard-Vicuna-13B-Uncensored](https://huggingface.co/cognitivecomputations/Wizard-Vicuna-13B-Uncensored)
|
| 32 |
+
|
| 33 |
+
## Run with LlamaEdge
|
| 34 |
+
|
| 35 |
+
- LlamaEdge version: [v0.2.4](https://github.com/second-state/LlamaEdge/releases/tag/0.2.4)
|
| 36 |
+
|
| 37 |
+
- Prompt template
|
| 38 |
+
|
| 39 |
+
- Prompt type: `vicuna-chat`
|
| 40 |
+
|
| 41 |
+
- Prompt string
|
| 42 |
+
|
| 43 |
+
```text
|
| 44 |
+
{system} USER: {prompt} ASSISTANT:
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
- Run as LlamaEdge service
|
| 48 |
+
|
| 49 |
+
```bash
|
| 50 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:wizard-vicuna-13b-ggml-model-q8_0.gguf llama-api-server.wasm -p vicuna-chat
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
- Run as LlamaEdge command app
|
| 54 |
+
|
| 55 |
+
```bash
|
| 56 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:wizard-vicuna-13b-ggml-model-q8_0.gguf llama-chat.wasm -p vicuna-chat
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
## Quantized GGUF Models
|
| 60 |
+
|
| 61 |
+
| Name | Quant method | Bits | Size | Use case |
|
| 62 |
+
| ---- | ---- | ---- | ---- | ----- |
|
| 63 |
+
| [Wizard-Vicuna-13B-Uncensored-Q2_K.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q2_K.gguf) | Q2_K | 2 | 4.85 GB| smallest, significant quality loss - not recommended for most purposes |
|
| 64 |
+
| [Wizard-Vicuna-13B-Uncensored-Q3_K_L.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| small, substantial quality loss |
|
| 65 |
+
| [Wizard-Vicuna-13B-Uncensored-Q3_K_M.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| very small, high quality loss |
|
| 66 |
+
| [Wizard-Vicuna-13B-Uncensored-Q3_K_S.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| very small, high quality loss |
|
| 67 |
+
| [Wizard-Vicuna-13B-Uncensored-Q4_0.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 68 |
+
| [Wizard-Vicuna-13B-Uncensored-Q4_K_M.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| medium, balanced quality - recommended |
|
| 69 |
+
| [Wizard-Vicuna-13B-Uncensored-Q4_K_S.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q4_K_S.gguf) | Q4_K_S | 4 | 7.42 GB| small, greater quality loss |
|
| 70 |
+
| [Wizard-Vicuna-13B-Uncensored-Q5_0.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 71 |
+
| [Wizard-Vicuna-13B-Uncensored-Q5_K_M.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| large, very low quality loss - recommended |
|
| 72 |
+
| [Wizard-Vicuna-13B-Uncensored-Q5_K_S.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| large, low quality loss - recommended |
|
| 73 |
+
| [Wizard-Vicuna-13B-Uncensored-Q6_K.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q6_K.gguf) | Q6_K | 6 | 10.7 GB| very large, extremely low quality loss |
|
| 74 |
+
| [Wizard-Vicuna-13B-Uncensored-Q8_0.gguf](https://huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF/blob/main/Wizard-Vicuna-13B-Uncensored-Q8_0.gguf) | Q8_0 | 8 | 13.8 GB| very large, extremely low quality loss - not recommended |
|