Upload folder using huggingface_hub
Browse files- .gitattributes +15 -0
- Llama3-70B-ShiningValiant2-Q2_K.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q3_K_L.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q3_K_M.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q3_K_S.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q4_0.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q4_K_M.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q4_K_S.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q5_0.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q5_K_M.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q5_K_S.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q6_K/Llama3-70B-ShiningValiant2-Q6_K-00001-of-00002.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q6_K/Llama3-70B-ShiningValiant2-Q6_K-00002-of-00002.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00001-of-00003.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00002-of-00003.gguf +3 -0
- Llama3-70B-ShiningValiant2-Q8_0/Llama3-70B-ShiningValiant2-Q8_0-00003-of-00003.gguf +3 -0
- README.md +96 -0
.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 |
+
```
|