morriszms commited on
Commit
e6d565a
·
verified ·
1 Parent(s): aaf6ded

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
+ mpt-7b-8k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ mpt-7b-8k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ mpt-7b-8k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ mpt-7b-8k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ mpt-7b-8k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ mpt-7b-8k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ mpt-7b-8k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ mpt-7b-8k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ mpt-7b-8k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ mpt-7b-8k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ mpt-7b-8k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ mpt-7b-8k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - Composer
5
+ - MosaicML
6
+ - llm-foundry
7
+ - StreamingDatasets
8
+ - TensorBlock
9
+ - GGUF
10
+ datasets:
11
+ - mc4
12
+ - c4
13
+ - togethercomputer/RedPajama-Data-1T
14
+ - bigcode/the-stack
15
+ - allenai/s2orc
16
+ inference: false
17
+ base_model: mosaicml/mpt-7b-8k
18
+ ---
19
+
20
+ <div style="width: auto; margin-left: auto; margin-right: auto">
21
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
+ </div>
23
+ <div style="display: flex; justify-content: space-between; width: 100%;">
24
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
25
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
26
+ 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>
27
+ </p>
28
+ </div>
29
+ </div>
30
+
31
+ ## mosaicml/mpt-7b-8k - GGUF
32
+
33
+ This repo contains GGUF format model files for [mosaicml/mpt-7b-8k](https://huggingface.co/mosaicml/mpt-7b-8k).
34
+
35
+ 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).
36
+
37
+ ## Our projects
38
+ <table border="1" cellspacing="0" cellpadding="10">
39
+ <tr>
40
+ <th style="font-size: 25px;">Awesome MCP Servers</th>
41
+ <th style="font-size: 25px;">TensorBlock Studio</th>
42
+ </tr>
43
+ <tr>
44
+ <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
45
+ <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
46
+ </tr>
47
+ <tr>
48
+ <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
49
+ <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
50
+ </tr>
51
+ <tr>
52
+ <th>
53
+ <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
54
+ display: inline-block;
55
+ padding: 8px 16px;
56
+ background-color: #FF7F50;
57
+ color: white;
58
+ text-decoration: none;
59
+ border-radius: 6px;
60
+ font-weight: bold;
61
+ font-family: sans-serif;
62
+ ">👀 See what we built 👀</a>
63
+ </th>
64
+ <th>
65
+ <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
66
+ display: inline-block;
67
+ padding: 8px 16px;
68
+ background-color: #FF7F50;
69
+ color: white;
70
+ text-decoration: none;
71
+ border-radius: 6px;
72
+ font-weight: bold;
73
+ font-family: sans-serif;
74
+ ">👀 See what we built 👀</a>
75
+ </th>
76
+ </tr>
77
+ </table>
78
+
79
+ ## Prompt template
80
+
81
+ ```
82
+ Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
83
+ ```
84
+
85
+ ## Model file specification
86
+
87
+ | Filename | Quant type | File Size | Description |
88
+ | -------- | ---------- | --------- | ----------- |
89
+ | [mpt-7b-8k-Q2_K.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q2_K.gguf) | Q2_K | 2.559 GB | smallest, significant quality loss - not recommended for most purposes |
90
+ | [mpt-7b-8k-Q3_K_S.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q3_K_S.gguf) | Q3_K_S | 2.941 GB | very small, high quality loss |
91
+ | [mpt-7b-8k-Q3_K_M.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q3_K_M.gguf) | Q3_K_M | 3.528 GB | very small, high quality loss |
92
+ | [mpt-7b-8k-Q3_K_L.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q3_K_L.gguf) | Q3_K_L | 3.847 GB | small, substantial quality loss |
93
+ | [mpt-7b-8k-Q4_0.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q4_0.gguf) | Q4_0 | 3.796 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
94
+ | [mpt-7b-8k-Q4_K_S.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q4_K_S.gguf) | Q4_K_S | 3.830 GB | small, greater quality loss |
95
+ | [mpt-7b-8k-Q4_K_M.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q4_K_M.gguf) | Q4_K_M | 4.274 GB | medium, balanced quality - recommended |
96
+ | [mpt-7b-8k-Q5_0.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q5_0.gguf) | Q5_0 | 4.601 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
97
+ | [mpt-7b-8k-Q5_K_S.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q5_K_S.gguf) | Q5_K_S | 4.601 GB | large, low quality loss - recommended |
98
+ | [mpt-7b-8k-Q5_K_M.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q5_K_M.gguf) | Q5_K_M | 4.958 GB | large, very low quality loss - recommended |
99
+ | [mpt-7b-8k-Q6_K.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q6_K.gguf) | Q6_K | 5.457 GB | very large, extremely low quality loss |
100
+ | [mpt-7b-8k-Q8_0.gguf](https://huggingface.co/tensorblock/mosaicml_mpt-7b-8k-GGUF/blob/main/mpt-7b-8k-Q8_0.gguf) | Q8_0 | 7.067 GB | very large, extremely low quality loss - not recommended |
101
+
102
+
103
+ ## Downloading instruction
104
+
105
+ ### Command line
106
+
107
+ Firstly, install Huggingface Client
108
+
109
+ ```shell
110
+ pip install -U "huggingface_hub[cli]"
111
+ ```
112
+
113
+ Then, downoad the individual model file the a local directory
114
+
115
+ ```shell
116
+ huggingface-cli download tensorblock/mosaicml_mpt-7b-8k-GGUF --include "mpt-7b-8k-Q2_K.gguf" --local-dir MY_LOCAL_DIR
117
+ ```
118
+
119
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
120
+
121
+ ```shell
122
+ huggingface-cli download tensorblock/mosaicml_mpt-7b-8k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
123
+ ```
mpt-7b-8k-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071e41c2429f7baf762d1ddabaaa86f232cc4d32a5652ad77bfac21b92b57824
3
+ size 2558859520
mpt-7b-8k-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a86b591eeae300bad78be52bad15db998ee91d6293a732e3ab15c0dfe203e4
3
+ size 3846510848
mpt-7b-8k-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92acbee48660ab032b11fb61f95b0bccc30d7ef48d7c70a6a2c808391fef1c0e
3
+ size 3527743744
mpt-7b-8k-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40fb5aa0d7652bdacc542b4a6b84559877d178c63c4f3365802c8f84a9537b3
3
+ size 2940541184
mpt-7b-8k-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5248b00d294895d8d995c18b3d87afe2305c3fdf744d0c97fc390870eb97b690
3
+ size 3796179200
mpt-7b-8k-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd939fba4f5d3b895e615443b517b6672c3a1a2ad8d22fb3a634519a7ca4874
3
+ size 4274329856
mpt-7b-8k-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8051f6e18193375518a1bccb03154c446135abd80fde73d99c01dec9a6bb7226
3
+ size 3829733632
mpt-7b-8k-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495e10767e5ae7b14320d0ee54531df225f5704ec6e97280342f98aae9a3a685
3
+ size 4601485568
mpt-7b-8k-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3908c57cb0a8d359654e25650bf1c3d480f72ee84d975ac2cd007c985f851930
3
+ size 4958001408
mpt-7b-8k-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:929f22228ae44fe0f6aeeb15a230d61a45c314045bf6b963f825e28c563c5455
3
+ size 4601485568
mpt-7b-8k-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099fb1c1c7d91306fd1b48caf5850b890e7087c129107f7f222c9b1354367f8a
3
+ size 5457123584
mpt-7b-8k-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f3f74924b9f574a835b678da73bd0dfb6a2e619e9680f22b5f5b0762f54433
3
+ size 7067433216