morriszms commited on
Commit
c139d2b
·
verified ·
1 Parent(s): 02aa15e

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
+ Mediquad-4x7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Mediquad-4x7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Mediquad-4x7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Mediquad-4x7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Mediquad-4x7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Mediquad-4x7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Mediquad-4x7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Mediquad-4x7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Mediquad-4x7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Mediquad-4x7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Mediquad-4x7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Mediquad-4x7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Mediquad-4x7b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3073bc2f585c796554420a00611d623eb24e0b87350f4f195c7e7d70d44dc35d
3
+ size 7235468960
Mediquad-4x7b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:048d9344eec5239d22ed31e6a6a8f4542f8b62056aea802f1fd1f74d0d806c83
3
+ size 10294894240
Mediquad-4x7b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7021e05d076405f78a5e1911913f1bcb8c21dbeaa97c81387a42065a6e65ccf0
3
+ size 9488539296
Mediquad-4x7b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14fed1260946cff01e100e5fb3d573c749a235dcb9328fbe2e4c3c2eddc5046
3
+ size 8530140832
Mediquad-4x7b-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c595ade35c4e650b8fa3ad5ea8b3b83a1b8fecc6cb63d8359a6c182505c5a4
3
+ size 11132288672
Mediquad-4x7b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c973f4d3881e18a804714573fce9e2252dcd60655929d526b6a30d432f3ec59e
3
+ size 11945459360
Mediquad-4x7b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5246deb85ddafa59c35b84b8fb335a057dd8e48bd34c1de53c9dc57d75acc3
3
+ size 11230854816
Mediquad-4x7b-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44360dec4da6cd69958d46b566b444f0ca6ab1096cc7c5a5189fb29981a5c36
3
+ size 13581368992
Mediquad-4x7b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a056396005c5c69400df5aab486c9cc821d1d85f3acd479af99edade215d0ea9
3
+ size 14000275104
Mediquad-4x7b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891ea832fbee499d9774373ee05cb90f8f62b4c1ef54a455b012e99fd72eede9
3
+ size 13581368992
Mediquad-4x7b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1fbedd92ac96997ff9afa255f163531f4ab1908f593c42690f86ec1f432d183
3
+ size 16183516832
Mediquad-4x7b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005216018b9590319d049bb25a8f96e64abf524734fe84027be6295278e0aee8
3
+ size 20960353952
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - merge
6
+ - epfl-llm/meditron-7b
7
+ - chaoyi-wu/PMC_LLAMA_7B_10_epoch
8
+ - allenai/tulu-2-dpo-7b
9
+ - microsoft/Orca-2-7b
10
+ - TensorBlock
11
+ - GGUF
12
+ base_model: Technoculture/Mediquad-4x7b
13
+ ---
14
+
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+ <div style="display: flex; justify-content: space-between; width: 100%;">
19
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
20
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
21
+ 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>
22
+ </p>
23
+ </div>
24
+ </div>
25
+
26
+ ## Technoculture/Mediquad-4x7b - GGUF
27
+
28
+ This repo contains GGUF format model files for [Technoculture/Mediquad-4x7b](https://huggingface.co/Technoculture/Mediquad-4x7b).
29
+
30
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
31
+
32
+ <div style="text-align: left; margin: 20px 0;">
33
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
34
+ Run them on the TensorBlock client using your local machine ↗
35
+ </a>
36
+ </div>
37
+
38
+ ## Prompt template
39
+
40
+ ```
41
+
42
+ ```
43
+
44
+ ## Model file specification
45
+
46
+ | Filename | Quant type | File Size | Description |
47
+ | -------- | ---------- | --------- | ----------- |
48
+ | [Mediquad-4x7b-Q2_K.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q2_K.gguf) | Q2_K | 7.235 GB | smallest, significant quality loss - not recommended for most purposes |
49
+ | [Mediquad-4x7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q3_K_S.gguf) | Q3_K_S | 8.530 GB | very small, high quality loss |
50
+ | [Mediquad-4x7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q3_K_M.gguf) | Q3_K_M | 9.489 GB | very small, high quality loss |
51
+ | [Mediquad-4x7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q3_K_L.gguf) | Q3_K_L | 10.295 GB | small, substantial quality loss |
52
+ | [Mediquad-4x7b-Q4_0.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q4_0.gguf) | Q4_0 | 11.132 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
53
+ | [Mediquad-4x7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q4_K_S.gguf) | Q4_K_S | 11.231 GB | small, greater quality loss |
54
+ | [Mediquad-4x7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q4_K_M.gguf) | Q4_K_M | 11.945 GB | medium, balanced quality - recommended |
55
+ | [Mediquad-4x7b-Q5_0.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q5_0.gguf) | Q5_0 | 13.581 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
56
+ | [Mediquad-4x7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q5_K_S.gguf) | Q5_K_S | 13.581 GB | large, low quality loss - recommended |
57
+ | [Mediquad-4x7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q5_K_M.gguf) | Q5_K_M | 14.000 GB | large, very low quality loss - recommended |
58
+ | [Mediquad-4x7b-Q6_K.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q6_K.gguf) | Q6_K | 16.184 GB | very large, extremely low quality loss |
59
+ | [Mediquad-4x7b-Q8_0.gguf](https://huggingface.co/tensorblock/Mediquad-4x7b-GGUF/blob/main/Mediquad-4x7b-Q8_0.gguf) | Q8_0 | 20.960 GB | very large, extremely low quality loss - not recommended |
60
+
61
+
62
+ ## Downloading instruction
63
+
64
+ ### Command line
65
+
66
+ Firstly, install Huggingface Client
67
+
68
+ ```shell
69
+ pip install -U "huggingface_hub[cli]"
70
+ ```
71
+
72
+ Then, downoad the individual model file the a local directory
73
+
74
+ ```shell
75
+ huggingface-cli download tensorblock/Mediquad-4x7b-GGUF --include "Mediquad-4x7b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
76
+ ```
77
+
78
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
79
+
80
+ ```shell
81
+ huggingface-cli download tensorblock/Mediquad-4x7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
82
+ ```