Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- MiniCPM-2B-dpo-fp16-Q2_K.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q3_K_L.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q3_K_M.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q3_K_S.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q4_0.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q4_K_M.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q4_K_S.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q5_0.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q5_K_M.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q5_K_S.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q6_K.gguf +3 -0
- MiniCPM-2B-dpo-fp16-Q8_0.gguf +3 -0
- README.md +81 -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 |
+
MiniCPM-2B-dpo-fp16-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
MiniCPM-2B-dpo-fp16-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
MiniCPM-2B-dpo-fp16-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
MiniCPM-2B-dpo-fp16-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
MiniCPM-2B-dpo-fp16-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
MiniCPM-2B-dpo-fp16-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
MiniCPM-2B-dpo-fp16-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
MiniCPM-2B-dpo-fp16-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
MiniCPM-2B-dpo-fp16-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
MiniCPM-2B-dpo-fp16-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
MiniCPM-2B-dpo-fp16-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
MiniCPM-2B-dpo-fp16-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
MiniCPM-2B-dpo-fp16-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:959b8a132cd44100bb5df3017602fa6a52ba82d5252139be95215f1d2a26c713
|
3 |
+
size 1204392640
|
MiniCPM-2B-dpo-fp16-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:189fd6922e1a81afc6b23402e4389ac3041c78a65d7ce11ca03c1c9a9cd297f5
|
3 |
+
size 1564369600
|
MiniCPM-2B-dpo-fp16-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:360e5159c21d32c2947f0c2a9117de9d1d056eb6748e203ba1d35c7614425df4
|
3 |
+
size 1481093824
|
MiniCPM-2B-dpo-fp16-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74637666e802ac636fed4e20b65b9108e0c56ba7934f35736e3f86546fb6eb80
|
3 |
+
size 1355350720
|
MiniCPM-2B-dpo-fp16-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e53831dee4002a552ab2b43b968b1c0f4293830b6374a38f63219128464db3b2
|
3 |
+
size 1609159360
|
MiniCPM-2B-dpo-fp16-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63ff98ef025ab020ac850fc90f0a3e06428038f699993ccfaa8193eef1a362b3
|
3 |
+
size 1802418880
|
MiniCPM-2B-dpo-fp16-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fec20c2b14ebd793196bc610ccf8b7b6a6e055cc27bbff3f0c2c5b9b1a590f18
|
3 |
+
size 1682315968
|
MiniCPM-2B-dpo-fp16-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:214603ed96a9dc8d69f34234cdbf0825f7a44d1f3f5c2c84d3c48f2d48522cd0
|
3 |
+
size 1914393280
|
MiniCPM-2B-dpo-fp16-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cb15c67fa7fa38d09201637fd3b9850b8264fdd5083f27ffa3a9e787323825c
|
3 |
+
size 2044615360
|
MiniCPM-2B-dpo-fp16-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:074affdad66f785d033016aed9e2a01d034399c359c3a4f5e00546cd41bd20ef
|
3 |
+
size 1947570880
|
MiniCPM-2B-dpo-fp16-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:733967e6b7ddd1de5684a1188018fad45a398f83bc4a6d1647a78a3be77dc196
|
3 |
+
size 2367267520
|
MiniCPM-2B-dpo-fp16-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f95029be2d18e1891986d7d1d32b9d4971c4a1d1c556d137d220e8d334aa8409
|
3 |
+
size 2898591200
|
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- zh
|
5 |
+
tags:
|
6 |
+
- MiniCPM
|
7 |
+
- ModelBest
|
8 |
+
- THUNLP
|
9 |
+
- TensorBlock
|
10 |
+
- GGUF
|
11 |
+
base_model: openbmb/MiniCPM-2B-dpo-fp16
|
12 |
+
---
|
13 |
+
|
14 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
15 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
16 |
+
</div>
|
17 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
18 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
19 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
20 |
+
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>
|
21 |
+
</p>
|
22 |
+
</div>
|
23 |
+
</div>
|
24 |
+
|
25 |
+
## openbmb/MiniCPM-2B-dpo-fp16 - GGUF
|
26 |
+
|
27 |
+
This repo contains GGUF format model files for [openbmb/MiniCPM-2B-dpo-fp16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-fp16).
|
28 |
+
|
29 |
+
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).
|
30 |
+
|
31 |
+
<div style="text-align: left; margin: 20px 0;">
|
32 |
+
<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;">
|
33 |
+
Run them on the TensorBlock client using your local machine ↗
|
34 |
+
</a>
|
35 |
+
</div>
|
36 |
+
|
37 |
+
## Prompt template
|
38 |
+
|
39 |
+
```
|
40 |
+
{system_prompt}<用户>{prompt}<AI>
|
41 |
+
```
|
42 |
+
|
43 |
+
## Model file specification
|
44 |
+
|
45 |
+
| Filename | Quant type | File Size | Description |
|
46 |
+
| -------- | ---------- | --------- | ----------- |
|
47 |
+
| [MiniCPM-2B-dpo-fp16-Q2_K.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q2_K.gguf) | Q2_K | 1.204 GB | smallest, significant quality loss - not recommended for most purposes |
|
48 |
+
| [MiniCPM-2B-dpo-fp16-Q3_K_S.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q3_K_S.gguf) | Q3_K_S | 1.355 GB | very small, high quality loss |
|
49 |
+
| [MiniCPM-2B-dpo-fp16-Q3_K_M.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q3_K_M.gguf) | Q3_K_M | 1.481 GB | very small, high quality loss |
|
50 |
+
| [MiniCPM-2B-dpo-fp16-Q3_K_L.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q3_K_L.gguf) | Q3_K_L | 1.564 GB | small, substantial quality loss |
|
51 |
+
| [MiniCPM-2B-dpo-fp16-Q4_0.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q4_0.gguf) | Q4_0 | 1.609 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
52 |
+
| [MiniCPM-2B-dpo-fp16-Q4_K_S.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q4_K_S.gguf) | Q4_K_S | 1.682 GB | small, greater quality loss |
|
53 |
+
| [MiniCPM-2B-dpo-fp16-Q4_K_M.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q4_K_M.gguf) | Q4_K_M | 1.802 GB | medium, balanced quality - recommended |
|
54 |
+
| [MiniCPM-2B-dpo-fp16-Q5_0.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q5_0.gguf) | Q5_0 | 1.914 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
55 |
+
| [MiniCPM-2B-dpo-fp16-Q5_K_S.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q5_K_S.gguf) | Q5_K_S | 1.948 GB | large, low quality loss - recommended |
|
56 |
+
| [MiniCPM-2B-dpo-fp16-Q5_K_M.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q5_K_M.gguf) | Q5_K_M | 2.045 GB | large, very low quality loss - recommended |
|
57 |
+
| [MiniCPM-2B-dpo-fp16-Q6_K.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q6_K.gguf) | Q6_K | 2.367 GB | very large, extremely low quality loss |
|
58 |
+
| [MiniCPM-2B-dpo-fp16-Q8_0.gguf](https://huggingface.co/tensorblock/MiniCPM-2B-dpo-fp16-GGUF/blob/main/MiniCPM-2B-dpo-fp16-Q8_0.gguf) | Q8_0 | 2.899 GB | very large, extremely low quality loss - not recommended |
|
59 |
+
|
60 |
+
|
61 |
+
## Downloading instruction
|
62 |
+
|
63 |
+
### Command line
|
64 |
+
|
65 |
+
Firstly, install Huggingface Client
|
66 |
+
|
67 |
+
```shell
|
68 |
+
pip install -U "huggingface_hub[cli]"
|
69 |
+
```
|
70 |
+
|
71 |
+
Then, downoad the individual model file the a local directory
|
72 |
+
|
73 |
+
```shell
|
74 |
+
huggingface-cli download tensorblock/MiniCPM-2B-dpo-fp16-GGUF --include "MiniCPM-2B-dpo-fp16-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
75 |
+
```
|
76 |
+
|
77 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
78 |
+
|
79 |
+
```shell
|
80 |
+
huggingface-cli download tensorblock/MiniCPM-2B-dpo-fp16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
81 |
+
```
|