morriszms commited on
Commit
fa1577b
·
verified ·
1 Parent(s): 74e7345

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,18 @@ 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
+ Llama3-70B-ShiningValiant2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama3-70B-ShiningValiant2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama3-70B-ShiningValiant2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama3-70B-ShiningValiant2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama3-70B-ShiningValiant2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama3-70B-ShiningValiant2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama3-70B-ShiningValiant2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama3-70B-ShiningValiant2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Llama3-70B-ShiningValiant2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Llama3-70B-ShiningValiant2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Llama3-70B-ShiningValiant2-Q6_K/Llama3-70B-ShiningValiant2-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Llama3-70B-ShiningValiant2-Q6_K/Llama3-70B-ShiningValiant2-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
Llama3-70B-ShiningValiant2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3751daf462d2ebbe9d23f3445395d8aa679250574bee51d099fd81142e770c8d
3
+ size 26375108736
Llama3-70B-ShiningValiant2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4ffdf57c94bf0f1f1cf88d0218a17f20901a8cbb48e17e1fd11984b3694d36
3
+ size 37140592768
Llama3-70B-ShiningValiant2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17375c46640e4b341004e0e0d0a3958e22eda6248963f1108485082766a307f4
3
+ size 34267494528
Llama3-70B-ShiningValiant2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b419ae910d22fe70ff4e96d298d39d70e01e613021ae73b7f6b6529f1eeb23f
3
+ size 30912051328
Llama3-70B-ShiningValiant2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e45fda24597faf45eed4add2a43c54d7064dcc1a5693ef5a1d89e3d32186c09d
3
+ size 39969732736
Llama3-70B-ShiningValiant2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa553fa2246e66689fbdf45c6b2c2f57fd6afe84ea59cd642ccaea3dcfbf411
3
+ size 42520393856
Llama3-70B-ShiningValiant2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b84537134419f19b97aef06e3c2f580ff7611cb1f35f90aa094661af2d5247
3
+ size 40347220096
Llama3-70B-ShiningValiant2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161822ca90a7a6a1a0abfa94e171cfe40da07086d51d18754574e1a9e6b89ce1
3
+ size 48657447040
Llama3-70B-ShiningValiant2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c242ea3f4c8613d57714f45d11f679b22d6cd8f2ac67bbad54179cd0a37f5e4d
3
+ size 49949816960
Llama3-70B-ShiningValiant2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1debade46b070b77857f8fbf770e686df45ab284cc9b618ff646b8a307ff72
3
+ size 48657447040
Llama3-70B-ShiningValiant2-Q6_K/Llama3-70B-ShiningValiant2-Q6_K-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286db5deb47586fbdc46e730214d20ebc5970729151a780326742e9ce47f0c4e
3
+ size 34847470752
Llama3-70B-ShiningValiant2-Q6_K/Llama3-70B-ShiningValiant2-Q6_K-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8e22c9b16fb7ea077c862fc0d6ef7ab0d56b413a938a8db463bad57c31e1f6
3
+ size 23040672928
Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86450d109b650f1fb3b469266503622a3aedbf8e30edd839ffc0ef34731dcfd
3
+ size 34980011200
Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6825d701d0d5cd7211ac3cd01bcb31d25a08692c7e4c14fa983174eaf49660f0
3
+ size 34949976384
Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92043c07fb03a776a4ad779cb717c8c66bd81af8d0010ac5346cdf4b8c5baed7
3
+ size 5045062560
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - shining-valiant
7
+ - shining-valiant-2
8
+ - valiant
9
+ - valiant-labs
10
+ - llama
11
+ - llama-3
12
+ - llama-3-instruct
13
+ - llama-3-instruct-70b
14
+ - 70b
15
+ - conversational
16
+ - chat
17
+ - instruct
18
+ - TensorBlock
19
+ - GGUF
20
+ model_type: llama
21
+ license: llama3
22
+ base_model: ValiantLabs/Llama3-70B-ShiningValiant2
23
+ ---
24
+
25
+ <div style="width: auto; margin-left: auto; margin-right: auto">
26
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
27
+ </div>
28
+ <div style="display: flex; justify-content: space-between; width: 100%;">
29
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
30
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
31
+ 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>
32
+ </p>
33
+ </div>
34
+ </div>
35
+
36
+ ## ValiantLabs/Llama3-70B-ShiningValiant2 - GGUF
37
+
38
+ This repo contains GGUF format model files for [ValiantLabs/Llama3-70B-ShiningValiant2](https://huggingface.co/ValiantLabs/Llama3-70B-ShiningValiant2).
39
+
40
+ 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).
41
+
42
+ <div style="text-align: left; margin: 20px 0;">
43
+ <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;">
44
+ Run them on the TensorBlock client using your local machine ↗
45
+ </a>
46
+ </div>
47
+
48
+ ## Prompt template
49
+
50
+ ```
51
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
52
+
53
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
54
+
55
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
56
+ ```
57
+
58
+ ## Model file specification
59
+
60
+ | Filename | Quant type | File Size | Description |
61
+ | -------- | ---------- | --------- | ----------- |
62
+ | [Llama3-70B-ShiningValiant2-Q2_K.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
63
+ | [Llama3-70B-ShiningValiant2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
64
+ | [Llama3-70B-ShiningValiant2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
65
+ | [Llama3-70B-ShiningValiant2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
66
+ | [Llama3-70B-ShiningValiant2-Q4_0.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
67
+ | [Llama3-70B-ShiningValiant2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
68
+ | [Llama3-70B-ShiningValiant2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
69
+ | [Llama3-70B-ShiningValiant2-Q5_0.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
70
+ | [Llama3-70B-ShiningValiant2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
71
+ | [Llama3-70B-ShiningValiant2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
72
+ | [Llama3-70B-ShiningValiant2-Q8_0](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q8_0) | Q6_K | 74.975 GB | very large, extremely low quality loss |
73
+ | [Llama3-70B-ShiningValiant2-Q6_K](https://huggingface.co/tensorblock/Llama3-70B-ShiningValiant2-GGUF/blob/main/Llama3-70B-ShiningValiant2-Q6_K) | Q8_0 | 57.888 GB | very large, extremely low quality loss - not recommended |
74
+
75
+
76
+ ## Downloading instruction
77
+
78
+ ### Command line
79
+
80
+ Firstly, install Huggingface Client
81
+
82
+ ```shell
83
+ pip install -U "huggingface_hub[cli]"
84
+ ```
85
+
86
+ Then, downoad the individual model file the a local directory
87
+
88
+ ```shell
89
+ huggingface-cli download tensorblock/Llama3-70B-ShiningValiant2-GGUF --include "Llama3-70B-ShiningValiant2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
90
+ ```
91
+
92
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
93
+
94
+ ```shell
95
+ huggingface-cli download tensorblock/Llama3-70B-ShiningValiant2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
96
+ ```