morriszms commited on
Commit
2c71600
Β·
verified Β·
1 Parent(s): 90cc622

Upload folder using huggingface_hub

Browse files
.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
+ Qwen3-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen3-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen3-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen3-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen3-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen3-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen3-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen3-4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen3-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen3-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen3-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen3-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen3-4B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6e003c774d29c93031bea15e38fca43a1685ad7f57caa25c9f19c803da60ec
3
+ size 1669494944
Qwen3-4B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4f1d7942148d7f0d8d5bc1ccfadc6d303cfbcb95ccfe3d47cca07c4c29fc79
3
+ size 2239781024
Qwen3-4B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015fc159c03c46c4c5811a66ede6aebebadf614598349077abffc6e65c981e2b
3
+ size 2075613344
Qwen3-4B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52eea87c50a98ba7a91b72a647049219184790153268b57c7b972a1b418da045
3
+ size 1886992544
Qwen3-4B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e537830386359c975d4db92fcf05ba144da75d2c1075d83f25bffd0cd00f434e
3
+ size 2369542304
Qwen3-4B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3694ed2a7d24cf020ad13fb24a9dc359d2688132f908f369ed28c2f01a3d3f5d
3
+ size 2497276064
Qwen3-4B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f667ef899befc4a48cc5761ea54a2f610a1cb8704938472209ce61660424a1c8
3
+ size 2383304864
Qwen3-4B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a75301d03ae798332713dedcbff2a43c76a5cfc8eef18510da8081597a43f5e5
3
+ size 2823706784
Qwen3-4B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3958059f86c516872fe576ece8c7aa6c3ab17c214dd730e12a2978b7b0d4275
3
+ size 2889509024
Qwen3-4B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcecd6e3baea0b7109cde1c71d9730cafc4bac3360134cad42953f6ca98603b3
3
+ size 2823706784
Qwen3-4B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7935d3df2b09d952a9ce238fb39e221e498b584dc37223037924e7f6abe21f88
3
+ size 3306256544
Qwen3-4B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc2f48ba8318f52c39ef6ad9616aea11d563e67b332b5f0f2a7417a2fce115e
3
+ size 4280400544
README.md ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - TensorBlock
5
+ - GGUF
6
+ base_model: willcb/Qwen3-4B
7
+ ---
8
+
9
+ <div style="width: auto; margin-left: auto; margin-right: auto">
10
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
11
+ </div>
12
+
13
+ [![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)
14
+ [![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)
15
+ [![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)
16
+ [![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)
17
+ [![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)
18
+
19
+
20
+ ## willcb/Qwen3-4B - GGUF
21
+
22
+ <div style="text-align: left; margin: 20px 0;">
23
+ <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;">
24
+ Join our Discord to learn more about what we're building β†—
25
+ </a>
26
+ </div>
27
+
28
+ This repo contains GGUF format model files for [willcb/Qwen3-4B](https://huggingface.co/willcb/Qwen3-4B).
29
+
30
+ 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).
31
+
32
+ ## Our projects
33
+ <table border="1" cellspacing="0" cellpadding="10">
34
+ <tr>
35
+ <th colspan="2" style="font-size: 25px;">Forge</th>
36
+ </tr>
37
+ <tr>
38
+ <th colspan="2">
39
+ <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
40
+ </th>
41
+ </tr>
42
+ <tr>
43
+ <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
44
+ </tr>
45
+ <tr>
46
+ <th colspan="2">
47
+ <a href="https://github.com/TensorBlock/forge" target="_blank" style="
48
+ display: inline-block;
49
+ padding: 8px 16px;
50
+ background-color: #FF7F50;
51
+ color: white;
52
+ text-decoration: none;
53
+ border-radius: 6px;
54
+ font-weight: bold;
55
+ font-family: sans-serif;
56
+ ">πŸš€ Try it now! πŸš€</a>
57
+ </th>
58
+ </tr>
59
+
60
+ <tr>
61
+ <th style="font-size: 25px;">Awesome MCP Servers</th>
62
+ <th style="font-size: 25px;">TensorBlock Studio</th>
63
+ </tr>
64
+ <tr>
65
+ <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
66
+ <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
67
+ </tr>
68
+ <tr>
69
+ <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
70
+ <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
71
+ </tr>
72
+ <tr>
73
+ <th>
74
+ <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
75
+ display: inline-block;
76
+ padding: 8px 16px;
77
+ background-color: #FF7F50;
78
+ color: white;
79
+ text-decoration: none;
80
+ border-radius: 6px;
81
+ font-weight: bold;
82
+ font-family: sans-serif;
83
+ ">πŸ‘€ See what we built πŸ‘€</a>
84
+ </th>
85
+ <th>
86
+ <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
87
+ display: inline-block;
88
+ padding: 8px 16px;
89
+ background-color: #FF7F50;
90
+ color: white;
91
+ text-decoration: none;
92
+ border-radius: 6px;
93
+ font-weight: bold;
94
+ font-family: sans-serif;
95
+ ">πŸ‘€ See what we built πŸ‘€</a>
96
+ </th>
97
+ </tr>
98
+ </table>
99
+
100
+ ## Prompt template
101
+
102
+ ```
103
+ <|im_start|>system
104
+ {system_prompt}<|im_end|>
105
+ <|im_start|>user
106
+ {prompt}<|im_end|>
107
+ <|im_start|>assistant
108
+ ```
109
+
110
+ ## Model file specification
111
+
112
+ | Filename | Quant type | File Size | Description |
113
+ | -------- | ---------- | --------- | ----------- |
114
+ | [Qwen3-4B-Q2_K.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q2_K.gguf) | Q2_K | 1.669 GB | smallest, significant quality loss - not recommended for most purposes |
115
+ | [Qwen3-4B-Q3_K_S.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q3_K_S.gguf) | Q3_K_S | 1.887 GB | very small, high quality loss |
116
+ | [Qwen3-4B-Q3_K_M.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q3_K_M.gguf) | Q3_K_M | 2.076 GB | very small, high quality loss |
117
+ | [Qwen3-4B-Q3_K_L.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q3_K_L.gguf) | Q3_K_L | 2.240 GB | small, substantial quality loss |
118
+ | [Qwen3-4B-Q4_0.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q4_0.gguf) | Q4_0 | 2.370 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
119
+ | [Qwen3-4B-Q4_K_S.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q4_K_S.gguf) | Q4_K_S | 2.383 GB | small, greater quality loss |
120
+ | [Qwen3-4B-Q4_K_M.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q4_K_M.gguf) | Q4_K_M | 2.497 GB | medium, balanced quality - recommended |
121
+ | [Qwen3-4B-Q5_0.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q5_0.gguf) | Q5_0 | 2.824 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
122
+ | [Qwen3-4B-Q5_K_S.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q5_K_S.gguf) | Q5_K_S | 2.824 GB | large, low quality loss - recommended |
123
+ | [Qwen3-4B-Q5_K_M.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q5_K_M.gguf) | Q5_K_M | 2.890 GB | large, very low quality loss - recommended |
124
+ | [Qwen3-4B-Q6_K.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q6_K.gguf) | Q6_K | 3.306 GB | very large, extremely low quality loss |
125
+ | [Qwen3-4B-Q8_0.gguf](https://huggingface.co/tensorblock/willcb_Qwen3-4B-GGUF/blob/main/Qwen3-4B-Q8_0.gguf) | Q8_0 | 4.280 GB | very large, extremely low quality loss - not recommended |
126
+
127
+
128
+ ## Downloading instruction
129
+
130
+ ### Command line
131
+
132
+ Firstly, install Huggingface Client
133
+
134
+ ```shell
135
+ pip install -U "huggingface_hub[cli]"
136
+ ```
137
+
138
+ Then, downoad the individual model file the a local directory
139
+
140
+ ```shell
141
+ huggingface-cli download tensorblock/willcb_Qwen3-4B-GGUF --include "Qwen3-4B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
142
+ ```
143
+
144
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
145
+
146
+ ```shell
147
+ huggingface-cli download tensorblock/willcb_Qwen3-4B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
148
+ ```