61 lines
4.0 KiB
Markdown
61 lines
4.0 KiB
Markdown
|
---
|
||
|
|
base_model: Alibaba-NLP/gte-Qwen2-7B-instruct
|
||
|
|
license: apache-2.0
|
||
|
|
model_creator: Alibaba-NLP
|
||
|
|
model_name: gte-Qwen2-7B-instruct
|
||
|
|
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 -->
|
||
|
|
|
||
|
|
# gte-Qwen2-7B-instruct-GGUF
|
||
|
|
|
||
|
|
## Original Model
|
||
|
|
|
||
|
|
[Alibaba-NLP/gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct)
|
||
|
|
|
||
|
|
## Run with LlamaEdge
|
||
|
|
|
||
|
|
- LlamaEdge version: [v0.16.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.8)
|
||
|
|
|
||
|
|
- Prompt template
|
||
|
|
|
||
|
|
- Prompt type: `embedding`
|
||
|
|
|
||
|
|
- Context size: `128000`
|
||
|
|
|
||
|
|
- Run as LlamaEdge service
|
||
|
|
|
||
|
|
```bash
|
||
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:gte-Qwen2-7B-instruct-Q5_K_M.gguf \
|
||
|
|
llama-api-server.wasm \
|
||
|
|
--model-name gte-Qwen2-7B-instruct \
|
||
|
|
--prompt-template embedding \
|
||
|
|
--ctx-size 128000
|
||
|
|
```
|
||
|
|
|
||
|
|
## Quantized GGUF Models
|
||
|
|
|
||
|
|
| Name | Quant method | Bits | Size | Use case |
|
||
|
|
| ---- | ---- | ---- | ---- | ----- |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q2_K.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q2_K.gguf) | Q2_K | 2 | 3.01 GB| smallest, significant quality loss - not recommended for most purposes |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.09 GB| small, substantial quality loss |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.81 GB| very small, high quality loss |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.49 GB| very small, high quality loss |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q4_0.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q4_0.gguf) | Q4_0 | 4 | 4.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.68 GB| medium, balanced quality - recommended |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.46 GB| small, greater quality loss |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q5_0.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q5_0.gguf) | Q5_0 | 5 | 5.31 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.44 GB| large, very low quality loss - recommended |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.31 GB| large, low quality loss - recommended |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q6_K.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q6_K.gguf) | Q6_K | 6 | 6.25 GB| very large, extremely low quality loss |
|
||
|
|
| [gte-Qwen2-7B-instruct-Q8_0.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-Q8_0.gguf) | Q8_0 | 8 | 8.10 GB| very large, extremely low quality loss - not recommended |
|
||
|
|
| [gte-Qwen2-7B-instruct-f16.gguf](https://huggingface.co/second-state/gte-Qwen2-7B-instruct-GGUF/blob/main/gte-Qwen2-7B-instruct-f16.gguf) | f16 | 16 | 15.2 GB| |
|
||
|
|
|
||
|
|
*Quantized with llama.cpp b4754*
|