Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen3-Reranker-4B-Q2_K.gguf +3 -0
- Qwen3-Reranker-4B-Q3_K_L.gguf +3 -0
- Qwen3-Reranker-4B-Q3_K_M.gguf +3 -0
- Qwen3-Reranker-4B-Q3_K_S.gguf +3 -0
- Qwen3-Reranker-4B-Q4_0.gguf +3 -0
- Qwen3-Reranker-4B-Q4_K_M.gguf +3 -0
- Qwen3-Reranker-4B-Q4_K_S.gguf +3 -0
- Qwen3-Reranker-4B-Q5_0.gguf +3 -0
- Qwen3-Reranker-4B-Q5_K_M.gguf +3 -0
- Qwen3-Reranker-4B-Q5_K_S.gguf +3 -0
- Qwen3-Reranker-4B-Q6_K.gguf +3 -0
- Qwen3-Reranker-4B-Q8_0.gguf +3 -0
- README.md +124 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
Qwen3-Reranker-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Qwen3-Reranker-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Qwen3-Reranker-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Qwen3-Reranker-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Qwen3-Reranker-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Qwen3-Reranker-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
Qwen3-Reranker-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
Qwen3-Reranker-4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
Qwen3-Reranker-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
Qwen3-Reranker-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
Qwen3-Reranker-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
Qwen3-Reranker-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen3-Reranker-4B-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ee063442e2024540cff237f79f47632788e78cf0a393f9fe722b59304edd02b
|
| 3 |
+
size 1668932640
|
Qwen3-Reranker-4B-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:459ef8b45212cffc82329c7490840786bce93f9afe956d183e0a37bb11fa3149
|
| 3 |
+
size 2239218720
|
Qwen3-Reranker-4B-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bcf3e6cd9bdc9f7d1b1045f03f6885b934aea31118daf557334e8a9da5e4d82
|
| 3 |
+
size 2075051040
|
Qwen3-Reranker-4B-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd31959523e21d4b4149b95916b428fdde35146fcda325efe9950ddd4af9bd2b
|
| 3 |
+
size 1886430240
|
Qwen3-Reranker-4B-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c0b47a8c12fec6e1b79f125ea775f2e733c7b55caef084226e5f957bb6112a
|
| 3 |
+
size 2368980000
|
Qwen3-Reranker-4B-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:721e30fbf20b905fa27ae02a1ed4b82478a9f517f7bd1a8792954b65a74a1ed7
|
| 3 |
+
size 2496713760
|
Qwen3-Reranker-4B-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97001714d938ca74051ba84f421e1804533e2963a0282836e1c54c8e7981c222
|
| 3 |
+
size 2382742560
|
Qwen3-Reranker-4B-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08aec04b2dce69f54b7f02c6523d59a8e6caa766bc72022127ea05413e6279c0
|
| 3 |
+
size 2823144480
|
Qwen3-Reranker-4B-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ae462b3e7b9e41e0f397e12798406d915d9b83a517d4122a0b7b2aca9057fad
|
| 3 |
+
size 2888946720
|
Qwen3-Reranker-4B-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8c17c0f0e1b26f487f209e0a1619302db5d3471010e90822edee0164af559ad
|
| 3 |
+
size 2823144480
|
Qwen3-Reranker-4B-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10986bae5a411d06c1d2de5f0f4bceba46c8dddd3361fd2c316b03da32cdb72a
|
| 3 |
+
size 3305694240
|
Qwen3-Reranker-4B-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5da0348a2ab9bb9dacef5697fb104f074c3180c1ee9540c0b2ae61536fbe2b64
|
| 3 |
+
size 4279672672
|
README.md
ADDED
|
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3-Reranker-4B
|
| 4 |
+
library_name: transformers
|
| 5 |
+
pipeline_tag: text-ranking
|
| 6 |
+
tags:
|
| 7 |
+
- TensorBlock
|
| 8 |
+
- GGUF
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 12 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 13 |
+
</div>
|
| 14 |
+
|
| 15 |
+
[](https://tensorblock.co)
|
| 16 |
+
[](https://twitter.com/tensorblock_aoi)
|
| 17 |
+
[](https://discord.gg/Ej5NmeHFf2)
|
| 18 |
+
[](https://github.com/TensorBlock)
|
| 19 |
+
[](https://t.me/TensorBlock)
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## Qwen/Qwen3-Reranker-4B - GGUF
|
| 23 |
+
|
| 24 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 25 |
+
<a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
|
| 26 |
+
Join our Discord to learn more about what we're building โ
|
| 27 |
+
</a>
|
| 28 |
+
</div>
|
| 29 |
+
|
| 30 |
+
This repo contains GGUF format model files for [Qwen/Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B).
|
| 31 |
+
|
| 32 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
|
| 33 |
+
|
| 34 |
+
## Our projects
|
| 35 |
+
<table border="1" cellspacing="0" cellpadding="10">
|
| 36 |
+
<tr>
|
| 37 |
+
<th style="font-size: 25px;">Awesome MCP Servers</th>
|
| 38 |
+
<th style="font-size: 25px;">TensorBlock Studio</th>
|
| 39 |
+
</tr>
|
| 40 |
+
<tr>
|
| 41 |
+
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
|
| 42 |
+
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
|
| 43 |
+
</tr>
|
| 44 |
+
<tr>
|
| 45 |
+
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
|
| 46 |
+
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
|
| 47 |
+
</tr>
|
| 48 |
+
<tr>
|
| 49 |
+
<th>
|
| 50 |
+
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
|
| 51 |
+
display: inline-block;
|
| 52 |
+
padding: 8px 16px;
|
| 53 |
+
background-color: #FF7F50;
|
| 54 |
+
color: white;
|
| 55 |
+
text-decoration: none;
|
| 56 |
+
border-radius: 6px;
|
| 57 |
+
font-weight: bold;
|
| 58 |
+
font-family: sans-serif;
|
| 59 |
+
">๐ See what we built ๐</a>
|
| 60 |
+
</th>
|
| 61 |
+
<th>
|
| 62 |
+
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
|
| 63 |
+
display: inline-block;
|
| 64 |
+
padding: 8px 16px;
|
| 65 |
+
background-color: #FF7F50;
|
| 66 |
+
color: white;
|
| 67 |
+
text-decoration: none;
|
| 68 |
+
border-radius: 6px;
|
| 69 |
+
font-weight: bold;
|
| 70 |
+
font-family: sans-serif;
|
| 71 |
+
">๐ See what we built ๐</a>
|
| 72 |
+
</th>
|
| 73 |
+
</tr>
|
| 74 |
+
</table>
|
| 75 |
+
|
| 76 |
+
## Prompt template
|
| 77 |
+
|
| 78 |
+
```
|
| 79 |
+
<|im_start|>system
|
| 80 |
+
{system_prompt}<|im_end|>
|
| 81 |
+
<|im_start|>user
|
| 82 |
+
{prompt}<|im_end|>
|
| 83 |
+
<|im_start|>assistant
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
## Model file specification
|
| 87 |
+
|
| 88 |
+
| Filename | Quant type | File Size | Description |
|
| 89 |
+
| -------- | ---------- | --------- | ----------- |
|
| 90 |
+
| [Qwen3-Reranker-4B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q2_K.gguf) | Q2_K | 1.669 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 91 |
+
| [Qwen3-Reranker-4B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q3_K_S.gguf) | Q3_K_S | 1.886 GB | very small, high quality loss |
|
| 92 |
+
| [Qwen3-Reranker-4B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q3_K_M.gguf) | Q3_K_M | 2.075 GB | very small, high quality loss |
|
| 93 |
+
| [Qwen3-Reranker-4B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q3_K_L.gguf) | Q3_K_L | 2.239 GB | small, substantial quality loss |
|
| 94 |
+
| [Qwen3-Reranker-4B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q4_0.gguf) | Q4_0 | 2.369 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 95 |
+
| [Qwen3-Reranker-4B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q4_K_S.gguf) | Q4_K_S | 2.383 GB | small, greater quality loss |
|
| 96 |
+
| [Qwen3-Reranker-4B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q4_K_M.gguf) | Q4_K_M | 2.497 GB | medium, balanced quality - recommended |
|
| 97 |
+
| [Qwen3-Reranker-4B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q5_0.gguf) | Q5_0 | 2.823 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 98 |
+
| [Qwen3-Reranker-4B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q5_K_S.gguf) | Q5_K_S | 2.823 GB | large, low quality loss - recommended |
|
| 99 |
+
| [Qwen3-Reranker-4B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q5_K_M.gguf) | Q5_K_M | 2.889 GB | large, very low quality loss - recommended |
|
| 100 |
+
| [Qwen3-Reranker-4B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q6_K.gguf) | Q6_K | 3.306 GB | very large, extremely low quality loss |
|
| 101 |
+
| [Qwen3-Reranker-4B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen_Qwen3-Reranker-4B-GGUF/blob/main/Qwen3-Reranker-4B-Q8_0.gguf) | Q8_0 | 4.280 GB | very large, extremely low quality loss - not recommended |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
## Downloading instruction
|
| 105 |
+
|
| 106 |
+
### Command line
|
| 107 |
+
|
| 108 |
+
Firstly, install Huggingface Client
|
| 109 |
+
|
| 110 |
+
```shell
|
| 111 |
+
pip install -U "huggingface_hub[cli]"
|
| 112 |
+
```
|
| 113 |
+
|
| 114 |
+
Then, downoad the individual model file the a local directory
|
| 115 |
+
|
| 116 |
+
```shell
|
| 117 |
+
huggingface-cli download tensorblock/Qwen_Qwen3-Reranker-4B-GGUF --include "Qwen3-Reranker-4B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
| 118 |
+
```
|
| 119 |
+
|
| 120 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
| 121 |
+
|
| 122 |
+
```shell
|
| 123 |
+
huggingface-cli download tensorblock/Qwen_Qwen3-Reranker-4B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
| 124 |
+
```
|