Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +79 -0
- llama2-13b-dpo-v7-Q2_K.gguf +3 -0
- llama2-13b-dpo-v7-Q3_K_L.gguf +3 -0
- llama2-13b-dpo-v7-Q3_K_M.gguf +3 -0
- llama2-13b-dpo-v7-Q3_K_S.gguf +3 -0
- llama2-13b-dpo-v7-Q4_0.gguf +3 -0
- llama2-13b-dpo-v7-Q4_K_M.gguf +3 -0
- llama2-13b-dpo-v7-Q4_K_S.gguf +3 -0
- llama2-13b-dpo-v7-Q5_0.gguf +3 -0
- llama2-13b-dpo-v7-Q5_K_M.gguf +3 -0
- llama2-13b-dpo-v7-Q5_K_S.gguf +3 -0
- llama2-13b-dpo-v7-Q6_K.gguf +3 -0
- llama2-13b-dpo-v7-Q8_0.gguf +3 -0
.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 |
+
llama2-13b-dpo-v7-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
llama2-13b-dpo-v7-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
llama2-13b-dpo-v7-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
llama2-13b-dpo-v7-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
llama2-13b-dpo-v7-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
llama2-13b-dpo-v7-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
llama2-13b-dpo-v7-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
llama2-13b-dpo-v7-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
llama2-13b-dpo-v7-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
llama2-13b-dpo-v7-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
llama2-13b-dpo-v7-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
llama2-13b-dpo-v7-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- ko
|
6 |
+
base_model: mncai/llama2-13b-dpo-v7
|
7 |
+
tags:
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
---
|
11 |
+
|
12 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
13 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
14 |
+
</div>
|
15 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
16 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
17 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
18 |
+
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>
|
19 |
+
</p>
|
20 |
+
</div>
|
21 |
+
</div>
|
22 |
+
|
23 |
+
## mncai/llama2-13b-dpo-v7 - GGUF
|
24 |
+
|
25 |
+
This repo contains GGUF format model files for [mncai/llama2-13b-dpo-v7](https://huggingface.co/mncai/llama2-13b-dpo-v7).
|
26 |
+
|
27 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
28 |
+
|
29 |
+
<div style="text-align: left; margin: 20px 0;">
|
30 |
+
<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;">
|
31 |
+
Run them on the TensorBlock client using your local machine ↗
|
32 |
+
</a>
|
33 |
+
</div>
|
34 |
+
|
35 |
+
## Prompt template
|
36 |
+
|
37 |
+
```
|
38 |
+
|
39 |
+
```
|
40 |
+
|
41 |
+
## Model file specification
|
42 |
+
|
43 |
+
| Filename | Quant type | File Size | Description |
|
44 |
+
| -------- | ---------- | --------- | ----------- |
|
45 |
+
| [llama2-13b-dpo-v7-Q2_K.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q2_K.gguf) | Q2_K | 4.600 GB | smallest, significant quality loss - not recommended for most purposes |
|
46 |
+
| [llama2-13b-dpo-v7-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q3_K_S.gguf) | Q3_K_S | 5.356 GB | very small, high quality loss |
|
47 |
+
| [llama2-13b-dpo-v7-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q3_K_M.gguf) | Q3_K_M | 5.988 GB | very small, high quality loss |
|
48 |
+
| [llama2-13b-dpo-v7-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q3_K_L.gguf) | Q3_K_L | 6.539 GB | small, substantial quality loss |
|
49 |
+
| [llama2-13b-dpo-v7-Q4_0.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q4_0.gguf) | Q4_0 | 6.955 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
50 |
+
| [llama2-13b-dpo-v7-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q4_K_S.gguf) | Q4_K_S | 7.008 GB | small, greater quality loss |
|
51 |
+
| [llama2-13b-dpo-v7-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q4_K_M.gguf) | Q4_K_M | 7.421 GB | medium, balanced quality - recommended |
|
52 |
+
| [llama2-13b-dpo-v7-Q5_0.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q5_0.gguf) | Q5_0 | 8.459 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
53 |
+
| [llama2-13b-dpo-v7-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q5_K_S.gguf) | Q5_K_S | 8.459 GB | large, low quality loss - recommended |
|
54 |
+
| [llama2-13b-dpo-v7-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q5_K_M.gguf) | Q5_K_M | 8.699 GB | large, very low quality loss - recommended |
|
55 |
+
| [llama2-13b-dpo-v7-Q6_K.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q6_K.gguf) | Q6_K | 10.058 GB | very large, extremely low quality loss |
|
56 |
+
| [llama2-13b-dpo-v7-Q8_0.gguf](https://huggingface.co/tensorblock/llama2-13b-dpo-v7-GGUF/blob/main/llama2-13b-dpo-v7-Q8_0.gguf) | Q8_0 | 13.027 GB | very large, extremely low quality loss - not recommended |
|
57 |
+
|
58 |
+
|
59 |
+
## Downloading instruction
|
60 |
+
|
61 |
+
### Command line
|
62 |
+
|
63 |
+
Firstly, install Huggingface Client
|
64 |
+
|
65 |
+
```shell
|
66 |
+
pip install -U "huggingface_hub[cli]"
|
67 |
+
```
|
68 |
+
|
69 |
+
Then, downoad the individual model file the a local directory
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/llama2-13b-dpo-v7-GGUF --include "llama2-13b-dpo-v7-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
73 |
+
```
|
74 |
+
|
75 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/llama2-13b-dpo-v7-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
79 |
+
```
|
llama2-13b-dpo-v7-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84c957d9cffeb4a49d85e571753cff6b6598e4a8af435f788030a61aa9528719
|
3 |
+
size 4938918080
|
llama2-13b-dpo-v7-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d13383edab2d2bea60722383d2d6c13f8fda9d8f0cee1fdca060441fc5bb329
|
3 |
+
size 7021662400
|
llama2-13b-dpo-v7-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c75e72781adfe40b21cdcfcd658ed2041914f2556c95386a6303751b2ab57fdb
|
3 |
+
size 6429872320
|
llama2-13b-dpo-v7-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98452b259f3a9f1785af8b966681447b55728a44bb2e8b9e8caa6eb4d4e4a6b1
|
3 |
+
size 5751083200
|
llama2-13b-dpo-v7-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:584d680dfbda9628621c3fba30aff308a63a9c7d3adcbce7a3b9cf55b22de364
|
3 |
+
size 7467686080
|
llama2-13b-dpo-v7-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fde9aa848bedee540e6e676f6886c523306d78d59706f5969d032b6224208fc
|
3 |
+
size 7967807680
|
llama2-13b-dpo-v7-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:094c6f2db8cd957f6b001b1628f0595f307d344f423f340b2057eafbf2d8b7d0
|
3 |
+
size 7525030080
|
llama2-13b-dpo-v7-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a8bc939451fa7230c7e2b01de32bbc5a2af02b8f729b82bb52847cddc59cbab
|
3 |
+
size 9083312320
|
llama2-13b-dpo-v7-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8985fb0d49c82fab5a153db9cea475f7d0dd28f12f638bcfe2d2160d252cf649
|
3 |
+
size 9340950720
|
llama2-13b-dpo-v7-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba066baf1cc19079b538bf42dabdbaf24b552c8c13d67111442c99eacc491494
|
3 |
+
size 9083312320
|
llama2-13b-dpo-v7-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8c7f1b305e6e27ccc9114e4024b91419487421f293e0519934d75a0da8f3c7b
|
3 |
+
size 10799915200
|
llama2-13b-dpo-v7-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0e00ca3cb8e8b8162cf27acf3348bc32f0f20c0be24ac9e63ba9ee7f4e4abe8
|
3 |
+
size 13987647680
|