79 lines
3.9 KiB
Markdown
79 lines
3.9 KiB
Markdown
|
---
|
||
|
|
base_model: Qwen/Qwen1.5-0.5B-Chat
|
||
|
|
license: other
|
||
|
|
license_name: tongyi-qianwen-research
|
||
|
|
license_link: >-
|
||
|
|
https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat/blob/main/LICENSE
|
||
|
|
model_creator: Qwen
|
||
|
|
model_name: Qwen1.5 0.5B Chat
|
||
|
|
quantized_by: Second State Inc.
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- chat
|
||
|
|
---
|
||
|
|
|
||
|
|
<!-- 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 -->
|
||
|
|
|
||
|
|
# Qwen1.5-0.5B-Chat-GGUF
|
||
|
|
|
||
|
|
## Original Model
|
||
|
|
|
||
|
|
[Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat)
|
||
|
|
|
||
|
|
## Run with LlamaEdge
|
||
|
|
|
||
|
|
- LlamaEdge version: [v0.2.15](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.15) and above
|
||
|
|
|
||
|
|
- Prompt template
|
||
|
|
|
||
|
|
- Prompt type: `chatml`
|
||
|
|
|
||
|
|
- Prompt string
|
||
|
|
|
||
|
|
```text
|
||
|
|
<|im_start|>system
|
||
|
|
{system_message}<|im_end|>
|
||
|
|
<|im_start|>user
|
||
|
|
{prompt}<|im_end|>
|
||
|
|
<|im_start|>assistant
|
||
|
|
```
|
||
|
|
|
||
|
|
- Context size: `32000`
|
||
|
|
|
||
|
|
- Run as LlamaEdge service
|
||
|
|
|
||
|
|
```bash
|
||
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-0.5B-Chat-Q5_K_M.gguf llama-api-server.wasm -p chatml
|
||
|
|
```
|
||
|
|
|
||
|
|
- Run as LlamaEdge command app
|
||
|
|
|
||
|
|
```bash
|
||
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-0.5B-Chat-Q5_K_M.gguf llama-chat.wasm -p chatml
|
||
|
|
```
|
||
|
|
|
||
|
|
## Quantized GGUF Models
|
||
|
|
|
||
|
|
| Name | Quant method | Bits | Size | Use case |
|
||
|
|
| ---- | ---- | ---- | ---- | ----- |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q2_K.gguf) | Q2_K | 2 | 298 MB| smallest, significant quality loss - not recommended for most purposes |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 364 MB| small, substantial quality loss |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 350 MB| very small, high quality loss |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 333 MB| very small, high quality loss |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q4_0.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q4_0.gguf) | Q4_0 | 4 | 395 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 407 MB| medium, balanced quality - recommended |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 397 MB| small, greater quality loss |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q5_0.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q5_0.gguf) | Q5_0 | 5 | 453 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 459 MB| large, very low quality loss - recommended |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 453 MB| large, low quality loss - recommended |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q6_K.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q6_K.gguf) | Q6_K | 6 | 515 MB| very large, extremely low quality loss |
|
||
|
|
| [Qwen1.5-0.5B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Qwen1.5-0.5B-Chat-GGUF/blob/main/Qwen1.5-0.5B-Chat-Q8_0.gguf) | Q8_0 | 8 | 665 MB| very large, extremely low quality loss - not recommended |
|