morriszms commited on
Commit
fcc73de
verified
1 Parent(s): 4e7c282

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
+ Ext2Gen-8B-R2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Ext2Gen-8B-R2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Ext2Gen-8B-R2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Ext2Gen-8B-R2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Ext2Gen-8B-R2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Ext2Gen-8B-R2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Ext2Gen-8B-R2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Ext2Gen-8B-R2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Ext2Gen-8B-R2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Ext2Gen-8B-R2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Ext2Gen-8B-R2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Ext2Gen-8B-R2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Ext2Gen-8B-R2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc9beb5259121d75f49dc152dd23da2fee4d87dd8c58fd24951b777fbb3b0b9
3
+ size 3179136288
Ext2Gen-8B-R2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2c80690630ff086ffb3f991e97e94fab136b7cac5e52131a2900af551484f7
3
+ size 4321961248
Ext2Gen-8B-R2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dedfee35f75a690a43574a82cc88338b37c6a13f56b7a6e4cb8603d58a28313
3
+ size 4018922784
Ext2Gen-8B-R2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef95ce1e7cf234635eb16fbfcb6e013728a714afd4617219d3dea2e5a603536c
3
+ size 3664504096
Ext2Gen-8B-R2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d4fe37e90ca1452964671babe9fc5518ca660fc89ee2023633a73acc8433a5
3
+ size 4661216544
Ext2Gen-8B-R2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bdcd0cd6a58287b7b6c2d0729be5f946f5c70340ef842d841c0dbec43d846c6
3
+ size 4920739104
Ext2Gen-8B-R2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78105901123198d8214e8e85da83534aa35e9c7df6737d6fd7ebe6c9e358aff0
3
+ size 4692673824
Ext2Gen-8B-R2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76815293671b95378cacc103402e28f2587ade63718b95d2410eaf3b797f1ca2
3
+ size 5599298848
Ext2Gen-8B-R2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f005370efb4564c67a14ff34c4c59b591598f1f87c0236f502be7bdec9dee21a
3
+ size 5732992288
Ext2Gen-8B-R2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5420be564fc10d82c2857cecc9003a267ee3dcbff05111aad0e8519651992817
3
+ size 5599298848
Ext2Gen-8B-R2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225fedad1d4135ee9b1d15765807d1ce8cbac53a8a62a636b542329319431c4a
3
+ size 6596011296
Ext2Gen-8B-R2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f415f17f4052487b89d3d75cc228ef31dd2e2ca2b62146a90b1dce62f77b1901
3
+ size 8540775712
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DISLab/Ext2Gen-8B-R2
3
+ language:
4
+ - en
5
+ license: apache-2.0
6
+ pipeline_tag: question-answering
7
+ tags:
8
+ - rag
9
+ - TensorBlock
10
+ - GGUF
11
+ library_name: transformers
12
+ ---
13
+
14
+ <div style="width: auto; margin-left: auto; margin-right: auto">
15
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
16
+ </div>
17
+ <div style="display: flex; justify-content: space-between; width: 100%;">
18
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
19
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
20
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
21
+ </p>
22
+ </div>
23
+ </div>
24
+
25
+ ## DISLab/Ext2Gen-8B-R2 - GGUF
26
+
27
+ This repo contains GGUF format model files for [DISLab/Ext2Gen-8B-R2](https://huggingface.co/DISLab/Ext2Gen-8B-R2).
28
+
29
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985).
30
+
31
+ ## Our projects
32
+ <table border="1" cellspacing="0" cellpadding="10">
33
+ <tr>
34
+ <th style="font-size: 25px;">Awesome MCP Servers</th>
35
+ <th style="font-size: 25px;">TensorBlock Studio</th>
36
+ </tr>
37
+ <tr>
38
+ <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
39
+ <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
40
+ </tr>
41
+ <tr>
42
+ <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
43
+ <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
44
+ </tr>
45
+ <tr>
46
+ <th>
47
+ <a href="https://github.com/TensorBlock/awesome-mcp-servers" 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
+ ">馃憖 See what we built 馃憖</a>
57
+ </th>
58
+ <th>
59
+ <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
60
+ display: inline-block;
61
+ padding: 8px 16px;
62
+ background-color: #FF7F50;
63
+ color: white;
64
+ text-decoration: none;
65
+ border-radius: 6px;
66
+ font-weight: bold;
67
+ font-family: sans-serif;
68
+ ">馃憖 See what we built 馃憖</a>
69
+ </th>
70
+ </tr>
71
+ </table>
72
+
73
+ ## Prompt template
74
+
75
+ ```
76
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
77
+
78
+ Cutting Knowledge Date: December 2023
79
+ Today Date: 26 Jul 2024
80
+
81
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
82
+
83
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
84
+ ```
85
+
86
+ ## Model file specification
87
+
88
+ | Filename | Quant type | File Size | Description |
89
+ | -------- | ---------- | --------- | ----------- |
90
+ | [Ext2Gen-8B-R2-Q2_K.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
91
+ | [Ext2Gen-8B-R2-Q3_K_S.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
92
+ | [Ext2Gen-8B-R2-Q3_K_M.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
93
+ | [Ext2Gen-8B-R2-Q3_K_L.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
94
+ | [Ext2Gen-8B-R2-Q4_0.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
95
+ | [Ext2Gen-8B-R2-Q4_K_S.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
96
+ | [Ext2Gen-8B-R2-Q4_K_M.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
97
+ | [Ext2Gen-8B-R2-Q5_0.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
98
+ | [Ext2Gen-8B-R2-Q5_K_S.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
99
+ | [Ext2Gen-8B-R2-Q5_K_M.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
100
+ | [Ext2Gen-8B-R2-Q6_K.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
101
+ | [Ext2Gen-8B-R2-Q8_0.gguf](https://huggingface.co/tensorblock/DISLab_Ext2Gen-8B-R2-GGUF/blob/main/Ext2Gen-8B-R2-Q8_0.gguf) | Q8_0 | 8.541 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/DISLab_Ext2Gen-8B-R2-GGUF --include "Ext2Gen-8B-R2-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/DISLab_Ext2Gen-8B-R2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
124
+ ```