Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- MoE_13B_DPO-Q2_K.gguf +3 -0
- MoE_13B_DPO-Q3_K_L.gguf +3 -0
- MoE_13B_DPO-Q3_K_M.gguf +3 -0
- MoE_13B_DPO-Q3_K_S.gguf +3 -0
- MoE_13B_DPO-Q4_0.gguf +3 -0
- MoE_13B_DPO-Q4_K_M.gguf +3 -0
- MoE_13B_DPO-Q4_K_S.gguf +3 -0
- MoE_13B_DPO-Q5_0.gguf +3 -0
- MoE_13B_DPO-Q5_K_M.gguf +3 -0
- MoE_13B_DPO-Q5_K_S.gguf +3 -0
- MoE_13B_DPO-Q6_K.gguf +3 -0
- MoE_13B_DPO-Q8_0.gguf +3 -0
- README.md +73 -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 |
+
MoE_13B_DPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
MoE_13B_DPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
MoE_13B_DPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
MoE_13B_DPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
MoE_13B_DPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
MoE_13B_DPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
MoE_13B_DPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
MoE_13B_DPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
MoE_13B_DPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
MoE_13B_DPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
MoE_13B_DPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
MoE_13B_DPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
MoE_13B_DPO-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:222fb60cada73ccdc7cfbd8eb3a0d3e21ac5c7cf7b1d881833ef8fc94d9892b5
|
3 |
+
size 4760823232
|
MoE_13B_DPO-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9ab1cdcd8aaed738f4aad23414e9a570efa9d74d80b00c1f938c592998f16a9
|
3 |
+
size 6729729472
|
MoE_13B_DPO-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c8c660a72c8d8854a0b205477c813bfa71ac5ba0016b1dda7a06041a5bdc9a8
|
3 |
+
size 6206490048
|
MoE_13B_DPO-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebd6bebe4ca34880c07f201acdc253af6ccb8989f2c8cf800338e986517ada41
|
3 |
+
size 5587830208
|
MoE_13B_DPO-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:734667e59aaf98fa3f1069368a8617939b89189c6e9f5c8546407c9803f33136
|
3 |
+
size 7280862656
|
MoE_13B_DPO-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:639d5ae8ee9bad01f4271891a13d0da4888ff18835474d3be24565dc7425e9ab
|
3 |
+
size 7782606272
|
MoE_13B_DPO-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1bb74290846ddcd194b57ea5c8b16acb39e9eaabd417311031047e54b04d3d2
|
3 |
+
size 7341680064
|
MoE_13B_DPO-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:032b6a9b4a16e05fb5d13b3556062d7b95609cff4bfe88eb2bfbd6668e96a8a8
|
3 |
+
size 8874304960
|
MoE_13B_DPO-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8cd347edb42a656e67b19f02da009261e9ecceabb1f89ec4122685c230346b4
|
3 |
+
size 9132778944
|
MoE_13B_DPO-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:903473cd35443d69d577687086cb1ab6169eb587f5f738bb7517e084acce52ce
|
3 |
+
size 8874304960
|
MoE_13B_DPO-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49c46fe6e1614eb812c17ff666c820c5fa150443321663ebb22460a0220ddf82
|
3 |
+
size 10567337408
|
MoE_13B_DPO-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbb2c7cb18b2485ac228be83a6ab5bf483caafdb7e9692df1b856f6aa90b6bd1
|
3 |
+
size 13686375872
|
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- DPO
|
6 |
+
- RL-TUNED
|
7 |
+
- TensorBlock
|
8 |
+
- GGUF
|
9 |
+
base_model: yunconglong/MoE_13B_DPO
|
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 |
+
## yunconglong/MoE_13B_DPO - GGUF
|
24 |
+
|
25 |
+
This repo contains GGUF format model files for [yunconglong/MoE_13B_DPO](https://huggingface.co/yunconglong/MoE_13B_DPO).
|
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 |
+
## Prompt template
|
30 |
+
|
31 |
+
```
|
32 |
+
|
33 |
+
```
|
34 |
+
|
35 |
+
## Model file specification
|
36 |
+
|
37 |
+
| Filename | Quant type | File Size | Description |
|
38 |
+
| -------- | ---------- | --------- | ----------- |
|
39 |
+
| [MoE_13B_DPO-Q2_K.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q2_K.gguf) | Q2_K | 4.434 GB | smallest, significant quality loss - not recommended for most purposes |
|
40 |
+
| [MoE_13B_DPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q3_K_S.gguf) | Q3_K_S | 5.204 GB | very small, high quality loss |
|
41 |
+
| [MoE_13B_DPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q3_K_M.gguf) | Q3_K_M | 5.780 GB | very small, high quality loss |
|
42 |
+
| [MoE_13B_DPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q3_K_L.gguf) | Q3_K_L | 6.268 GB | small, substantial quality loss |
|
43 |
+
| [MoE_13B_DPO-Q4_0.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q4_0.gguf) | Q4_0 | 6.781 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
44 |
+
| [MoE_13B_DPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q4_K_S.gguf) | Q4_K_S | 6.837 GB | small, greater quality loss |
|
45 |
+
| [MoE_13B_DPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q4_K_M.gguf) | Q4_K_M | 7.248 GB | medium, balanced quality - recommended |
|
46 |
+
| [MoE_13B_DPO-Q5_0.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q5_0.gguf) | Q5_0 | 8.265 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
47 |
+
| [MoE_13B_DPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q5_K_S.gguf) | Q5_K_S | 8.265 GB | large, low quality loss - recommended |
|
48 |
+
| [MoE_13B_DPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q5_K_M.gguf) | Q5_K_M | 8.506 GB | large, very low quality loss - recommended |
|
49 |
+
| [MoE_13B_DPO-Q6_K.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q6_K.gguf) | Q6_K | 9.842 GB | very large, extremely low quality loss |
|
50 |
+
| [MoE_13B_DPO-Q8_0.gguf](https://huggingface.co/tensorblock/MoE_13B_DPO-GGUF/tree/main/MoE_13B_DPO-Q8_0.gguf) | Q8_0 | 12.746 GB | very large, extremely low quality loss - not recommended |
|
51 |
+
|
52 |
+
|
53 |
+
## Downloading instruction
|
54 |
+
|
55 |
+
### Command line
|
56 |
+
|
57 |
+
Firstly, install Huggingface Client
|
58 |
+
|
59 |
+
```shell
|
60 |
+
pip install -U "huggingface_hub[cli]"
|
61 |
+
```
|
62 |
+
|
63 |
+
Then, downoad the individual model file the a local directory
|
64 |
+
|
65 |
+
```shell
|
66 |
+
huggingface-cli download tensorblock/MoE_13B_DPO-GGUF --include "MoE_13B_DPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
67 |
+
```
|
68 |
+
|
69 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/MoE_13B_DPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
73 |
+
```
|