|
--- |
|
license: other |
|
license_name: tongyi-qianwen |
|
license_link: >- |
|
https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE |
|
model_name: Qwen1.5-110B-Chat |
|
arxiv: 2307.09288 |
|
base_model: Qwen/Qwen1.5-110B-Chat |
|
inference: false |
|
model_creator: Qwen |
|
pipeline_tag: text-generation |
|
quantized_by: Second State Inc. |
|
language: |
|
- en |
|
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 --> |
|
|
|
# Qwen1.5-110B-Chat-GGUF |
|
|
|
## Original Model |
|
|
|
[Qwen/Qwen1.5-110B-Chat](https://huggingface.co/Qwen/Qwen1.5-110B-Chat) |
|
|
|
## Run with LlamaEdge |
|
|
|
- LlamaEdge version: [v0.10.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.10.0) 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:Qwen1.5-110B-Chat-Q2_K.gguf \ |
|
llama-api-server.wasm \ |
|
--prompt-template chatml \ |
|
--ctx-size 32000 \ |
|
--model-name qwen1.5-110b-chat |
|
``` |
|
|
|
- Run as LlamaEdge command app |
|
|
|
```bash |
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-110B-Chat-Q2_K.gguf \ |
|
llama-chat.wasm \ |
|
--prompt-template chatml \ |
|
--ctx-size 32000 |
|
``` |
|
|
|
## Quantized GGUF Models |
|
|
|
| Name | Quant method | Bits | Size | Use case | |
|
| ---- | ---- | ---- | ---- | ----- | |
|
| [Qwen1.5-110B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q2_K.gguf) | Q2_K | 2 | 41.2 GB| smallest, significant quality loss - not recommended for most purposes | |
|
| [Qwen1.5-110B-Chat-Q3_K_L-00001-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q3_K_L-00001-of-00002.gguf) | Q3_K_L | 3 | 32.2 GB| small, substantial quality loss | |
|
| [Qwen1.5-110B-Chat-Q3_K_L-00002-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q3_K_L-00002-of-00002.gguf) | Q3_K_L | 3 | 26 GB| small, substantial quality loss | |
|
| [Qwen1.5-110B-Chat-Q3_K_M-00001-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q3_K_M-00001-of-00002.gguf) | Q3_K_M | 3 | 32.2 GB| very small, high quality loss | |
|
| [Qwen1.5-110B-Chat-Q3_K_M-00002-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q3_K_M-00002-of-00002.gguf) | Q3_K_M | 3 | 21.5 GB| very small, high quality loss | |
|
| [Qwen1.5-110B-Chat-Q3_K_S-00001-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q3_K_S-00001-of-00002.gguf) | Q3_K_S | 3 | 32.2 GB| very small, high quality loss | |
|
| [Qwen1.5-110B-Chat-Q3_K_S-00002-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q3_K_S-00002-of-00002.gguf) | Q3_K_S | 3 | 16.3 GB| very small, high quality loss | |
|
| [Qwen1.5-110B-Chat-Q4_0-00001-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q4_0-00001-of-00002.gguf) | Q4_0 | 4 | 32.1 GB| legacy; small, very high quality loss - prefer using Q3_K_M | |
|
| [Qwen1.5-110B-Chat-Q4_0-00002-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q4_0-00002-of-00002.gguf) | Q4_0 | 4 | 30.8 GB| legacy; small, very high quality loss - prefer using Q3_K_M | |
|
| [Qwen1.5-110B-Chat-Q4_K_M-00001-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q4_K_M-00001-of-00003.gguf) | Q4_K_M | 4 | 32 GB| medium, balanced quality - recommended | |
|
| [Qwen1.5-110B-Chat-Q4_K_M-00002-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q4_K_M-00002-of-00003.gguf) | Q4_K_M | 4 | 32.1 GB| medium, balanced quality - recommended | |
|
| [Qwen1.5-110B-Chat-Q4_K_M-00003-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q4_K_M-00003-of-00003.gguf) | Q4_K_M | 4 | 3.09 GB| medium, balanced quality - recommended | |
|
| [Qwen1.5-110B-Chat-Q4_K_S-00001-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q4_K_S-00001-of-00002.gguf) | Q4_K_S | 4 | 32.1 GB| small, greater quality loss | |
|
| [Qwen1.5-110B-Chat-Q4_K_S-00002-of-00002.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q4_K_S-00002-of-00002.gguf) | Q4_K_S | 4 | 31.3 GB| small, greater quality loss | |
|
| [Qwen1.5-110B-Chat-Q5_0-00001-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_0-00001-of-00003.gguf) | Q5_0 | 5 | 32 GB| legacy; medium, balanced quality - prefer using Q4_K_M | |
|
| [Qwen1.5-110B-Chat-Q5_0-00002-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_0-00002-of-00003.gguf) | Q5_0 | 5 | 32.1 GB| legacy; medium, balanced quality - prefer using Q4_K_M | |
|
| [Qwen1.5-110B-Chat-Q5_0-00003-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_0-00003-of-00003.gguf) | Q5_0 | 5 | 12.5 GB| legacy; medium, balanced quality - prefer using Q4_K_M | |
|
| [Qwen1.5-110B-Chat-Q5_K_M-00001-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_K_M-00001-of-00003.gguf) | Q5_K_M | 5 | 32.1 GB| large, very low quality loss - recommended | |
|
| [Qwen1.5-110B-Chat-Q5_K_M-00002-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_K_M-00002-of-00003.gguf) | Q5_K_M | 5 | 32 GB| large, very low quality loss - recommended | |
|
| [Qwen1.5-110B-Chat-Q5_K_M-00003-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_K_M-00003-of-00003.gguf) | Q5_K_M | 5 | 14.8 GB| large, very low quality loss - recommended | |
|
| [Qwen1.5-110B-Chat-Q5_K_S-00001-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_K_S-00001-of-00003.gguf) | Q5_K_S | 5 | 32 GB| large, low quality loss - recommended | |
|
| [Qwen1.5-110B-Chat-Q5_K_S-00002-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_K_S-00002-of-00003.gguf) | Q5_K_S | 5 | 32.1 GB| large, low quality loss - recommended | |
|
| [Qwen1.5-110B-Chat-Q5_K_S-00003-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q5_K_S-00003-of-00003.gguf) | Q5_K_S | 5 | 12.5 GB| large, low quality loss - recommended | |
|
| [Qwen1.5-110B-Chat-Q6_K-00001-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q6_K-00001-of-00003.gguf) | Q6_K | 6 | 31.9 GB| very large, extremely low quality loss | |
|
| [Qwen1.5-110B-Chat-Q6_K-00002-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q6_K-00002-of-00003.gguf) | Q6_K | 6 | 32 GB| very large, extremely low quality loss | |
|
| [Qwen1.5-110B-Chat-Q6_K-00003-of-00003.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q6_K-00003-of-00003.gguf) | Q6_K | 6 | 27.3 GB| very large, extremely low quality loss | |
|
| [Qwen1.5-110B-Chat-Q8_0-00001-of-00004.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q8_0-00001-of-00004.gguf) | Q8_0 | 8 | 32.1 GB| very large, extremely low quality loss - not recommended | |
|
| [Qwen1.5-110B-Chat-Q8_0-00002-of-00004.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q8_0-00002-of-00004.gguf) | Q8_0 | 8 | 31.9 GB| very large, extremely low quality loss - not recommended | |
|
| [Qwen1.5-110B-Chat-Q8_0-00003-of-00004.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q8_0-00003-of-00004.gguf) | Q8_0 | 8 | 32.2 GB| very large, extremely low quality loss - not recommended | |
|
| [Qwen1.5-110B-Chat-Q8_0-00004-of-00004.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-Q8_0-00004-of-00004.gguf) | Q8_0 | 8 | 22 GB| very large, extremely low quality loss - not recommended | |
|
| [Qwen1.5-110B-Chat-f16-00001-of-00007.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-f16-00001-of-00007.gguf) | f16 | 16 | 31.9 GB| | |
|
| [Qwen1.5-110B-Chat-f16-00002-of-00007.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-f16-00002-of-00007.gguf) | f16 | 16 | 32 GB| | |
|
| [Qwen1.5-110B-Chat-f16-00003-of-00007.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-f16-00003-of-00007.gguf) | f16 | 16 | 31.8 GB| | |
|
| [Qwen1.5-110B-Chat-f16-00004-of-00007.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-f16-00004-of-00007.gguf) | f16 | 16 | 31.8 GB| | |
|
| [Qwen1.5-110B-Chat-f16-00005-of-00007.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-f16-00005-of-00007.gguf) | f16 | 16 | 31.8 GB| | |
|
| [Qwen1.5-110B-Chat-f16-00006-of-00007.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-f16-00006-of-00007.gguf) | f16 | 16 | 31.5 GB| | |
|
| [Qwen1.5-110B-Chat-f16-00007-of-00007.gguf](https://huggingface.co/second-state/Qwen1.5-110B-Chat-GGUF/blob/main/Qwen1.5-110B-Chat-f16-00007-of-00007.gguf) | f16 | 16 | 31.6 GB| | |
|
|
|
*Quantized with llama.cpp b2824.* |
|
|
