Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +69 -0
- llama2-7b-dpo-v1-Q2_K.gguf +3 -0
- llama2-7b-dpo-v1-Q3_K_L.gguf +3 -0
- llama2-7b-dpo-v1-Q3_K_M.gguf +3 -0
- llama2-7b-dpo-v1-Q3_K_S.gguf +3 -0
- llama2-7b-dpo-v1-Q4_0.gguf +3 -0
- llama2-7b-dpo-v1-Q4_K_M.gguf +3 -0
- llama2-7b-dpo-v1-Q4_K_S.gguf +3 -0
- llama2-7b-dpo-v1-Q5_0.gguf +3 -0
- llama2-7b-dpo-v1-Q5_K_M.gguf +3 -0
- llama2-7b-dpo-v1-Q5_K_S.gguf +3 -0
- llama2-7b-dpo-v1-Q6_K.gguf +3 -0
- llama2-7b-dpo-v1-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 |
+
llama2-7b-dpo-v1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
llama2-7b-dpo-v1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
llama2-7b-dpo-v1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
llama2-7b-dpo-v1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
llama2-7b-dpo-v1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
llama2-7b-dpo-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
llama2-7b-dpo-v1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
llama2-7b-dpo-v1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
llama2-7b-dpo-v1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
llama2-7b-dpo-v1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
llama2-7b-dpo-v1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
llama2-7b-dpo-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: mncai/llama2-7b-dpo-v1
|
3 |
+
tags:
|
4 |
+
- TensorBlock
|
5 |
+
- GGUF
|
6 |
+
---
|
7 |
+
|
8 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
9 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
10 |
+
</div>
|
11 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
12 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
13 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
14 |
+
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>
|
15 |
+
</p>
|
16 |
+
</div>
|
17 |
+
</div>
|
18 |
+
|
19 |
+
## mncai/llama2-7b-dpo-v1 - GGUF
|
20 |
+
|
21 |
+
This repo contains GGUF format model files for [mncai/llama2-7b-dpo-v1](https://huggingface.co/mncai/llama2-7b-dpo-v1).
|
22 |
+
|
23 |
+
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).
|
24 |
+
|
25 |
+
## Prompt template
|
26 |
+
|
27 |
+
```
|
28 |
+
|
29 |
+
```
|
30 |
+
|
31 |
+
## Model file specification
|
32 |
+
|
33 |
+
| Filename | Quant type | File Size | Description |
|
34 |
+
| -------- | ---------- | --------- | ----------- |
|
35 |
+
| [llama2-7b-dpo-v1-Q2_K.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q2_K.gguf) | Q2_K | 2.359 GB | smallest, significant quality loss - not recommended for most purposes |
|
36 |
+
| [llama2-7b-dpo-v1-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q3_K_S.gguf) | Q3_K_S | 2.746 GB | very small, high quality loss |
|
37 |
+
| [llama2-7b-dpo-v1-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q3_K_M.gguf) | Q3_K_M | 3.072 GB | very small, high quality loss |
|
38 |
+
| [llama2-7b-dpo-v1-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q3_K_L.gguf) | Q3_K_L | 3.350 GB | small, substantial quality loss |
|
39 |
+
| [llama2-7b-dpo-v1-Q4_0.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q4_0.gguf) | Q4_0 | 3.563 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
40 |
+
| [llama2-7b-dpo-v1-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q4_K_S.gguf) | Q4_K_S | 3.592 GB | small, greater quality loss |
|
41 |
+
| [llama2-7b-dpo-v1-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q4_K_M.gguf) | Q4_K_M | 3.801 GB | medium, balanced quality - recommended |
|
42 |
+
| [llama2-7b-dpo-v1-Q5_0.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q5_0.gguf) | Q5_0 | 4.332 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
43 |
+
| [llama2-7b-dpo-v1-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q5_K_S.gguf) | Q5_K_S | 4.332 GB | large, low quality loss - recommended |
|
44 |
+
| [llama2-7b-dpo-v1-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q5_K_M.gguf) | Q5_K_M | 4.455 GB | large, very low quality loss - recommended |
|
45 |
+
| [llama2-7b-dpo-v1-Q6_K.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q6_K.gguf) | Q6_K | 5.149 GB | very large, extremely low quality loss |
|
46 |
+
| [llama2-7b-dpo-v1-Q8_0.gguf](https://huggingface.co/tensorblock/llama2-7b-dpo-v1-GGUF/tree/main/llama2-7b-dpo-v1-Q8_0.gguf) | Q8_0 | 6.669 GB | very large, extremely low quality loss - not recommended |
|
47 |
+
|
48 |
+
|
49 |
+
## Downloading instruction
|
50 |
+
|
51 |
+
### Command line
|
52 |
+
|
53 |
+
Firstly, install Huggingface Client
|
54 |
+
|
55 |
+
```shell
|
56 |
+
pip install -U "huggingface_hub[cli]"
|
57 |
+
```
|
58 |
+
|
59 |
+
Then, downoad the individual model file the a local directory
|
60 |
+
|
61 |
+
```shell
|
62 |
+
huggingface-cli download tensorblock/llama2-7b-dpo-v1-GGUF --include "llama2-7b-dpo-v1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
63 |
+
```
|
64 |
+
|
65 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
66 |
+
|
67 |
+
```shell
|
68 |
+
huggingface-cli download tensorblock/llama2-7b-dpo-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
69 |
+
```
|
llama2-7b-dpo-v1-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb53107d462f50376bc430cac18b21733515a8ac1809e3c8c1a2a4ffa4471a2d
|
3 |
+
size 2532864160
|
llama2-7b-dpo-v1-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:643830619a5df421834fe950935bfc951abfdcb528d728bacd9cbfcf34245076
|
3 |
+
size 3597111456
|
llama2-7b-dpo-v1-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:095105da11f62ede3de63f27158fbd3d0342cdc28ba13cd9c23345022a24a729
|
3 |
+
size 3298005152
|
llama2-7b-dpo-v1-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cea0e1f33004e0e0d5a387fb712500b96346c5068eaf213398e325e78d45262
|
3 |
+
size 2948305056
|
llama2-7b-dpo-v1-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:027bc0fb47920f94c5571e3d020387657e30b6c370728501f84fe275a1bb4fc3
|
3 |
+
size 3825807520
|
llama2-7b-dpo-v1-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b80117bac6792042f7554c4ed8b0a409c4bf56084239d268fbdd9343a06785fe
|
3 |
+
size 4081004704
|
llama2-7b-dpo-v1-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7899bd395cd5547a3b0ebd88b4cf2a53c5f476d18b8d3a045a35cb19338a2209
|
3 |
+
size 3856740512
|
llama2-7b-dpo-v1-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eea8da1ed73a6ceccc554cb2b7c4cebc145392bb91d12ebf9d1b072233b612b4
|
3 |
+
size 4651692192
|
llama2-7b-dpo-v1-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e270c9d9648bd3b1de88a44671171c332b6b93c161fca799266602f6fb33e57
|
3 |
+
size 4783157408
|
llama2-7b-dpo-v1-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccd343df136f537f98b0799d0892dc13e0527dbc36c902fcc23900e567605578
|
3 |
+
size 4651692192
|
llama2-7b-dpo-v1-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:440c54173d92d1880958fac9934239159584a155e99e4a4944fc9e5adacb9200
|
3 |
+
size 5529194656
|
llama2-7b-dpo-v1-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f990f2d391f9547cc448a25ccdc010a4dc3edf7b768cee65a1ae8de7a0b5fb9
|
3 |
+
size 7161090208
|