Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- DeepSeek-V2-Lite-Chat-Q2_K.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q3_K_L.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q3_K_M.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q3_K_S.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q4_0.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q4_K_M.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q4_K_S.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q5_0.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q5_K_M.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q5_K_S.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q6_K.gguf +3 -0
- DeepSeek-V2-Lite-Chat-Q8_0.gguf +3 -0
- README.md +76 -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 |
+
DeepSeek-V2-Lite-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
DeepSeek-V2-Lite-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
DeepSeek-V2-Lite-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
DeepSeek-V2-Lite-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
DeepSeek-V2-Lite-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
DeepSeek-V2-Lite-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
DeepSeek-V2-Lite-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
DeepSeek-V2-Lite-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
DeepSeek-V2-Lite-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
DeepSeek-V2-Lite-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
DeepSeek-V2-Lite-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
DeepSeek-V2-Lite-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
DeepSeek-V2-Lite-Chat-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a77d1dab7fae74a0377a3803b7428e60643fd231d309e8718bcee4c8ecf9499d
|
3 |
+
size 6430464704
|
DeepSeek-V2-Lite-Chat-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31e58ceaff9bfa157e41345790b4d3f452df86b7ae81b03661651ab47ef60f78
|
3 |
+
size 8459398848
|
DeepSeek-V2-Lite-Chat-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1b37d75ce30728aaf6dfc5fdaca0e7a632bb0491ca206ef5b37995989282dd6
|
3 |
+
size 8126607040
|
DeepSeek-V2-Lite-Chat-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:588569c53601fb6fec8e104da3bd10d0802da7e7997cef6c0ddd01286b2ece69
|
3 |
+
size 7487663808
|
DeepSeek-V2-Lite-Chat-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6277b2c88b72cf79b06d33ec461b62cebf93afd9c828205587993fec03d73966
|
3 |
+
size 8905110208
|
DeepSeek-V2-Lite-Chat-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12705eccf3dc3b1d10f570b899b1326520a2886aa4689060bf6c40b17191c918
|
3 |
+
size 10364416704
|
DeepSeek-V2-Lite-Chat-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c6dec9bdc047f43984ebb0400a207d7ce55be96313587d9b9b77515073220b8
|
3 |
+
size 9533608640
|
DeepSeek-V2-Lite-Chat-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42639af2cbff3705b05dba0b37c45dc9b9d916eb561abe9ea383150ad1cec093
|
3 |
+
size 10841764544
|
DeepSeek-V2-Lite-Chat-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:758dc0787f5a88801ba41d7a432491728eb90d8af9f29b9e89cbc35500172b67
|
3 |
+
size 11851313856
|
DeepSeek-V2-Lite-Chat-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e04dcd559c1373fe6081aefb0c102e41eb11d16ff95b1f3ab4cf67f1cf178104
|
3 |
+
size 11143058112
|
DeepSeek-V2-Lite-Chat-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:509c84d6fdda5b8243f3a27efb052875f307cf77baa4e11f49222ba064cf8975
|
3 |
+
size 14066972352
|
DeepSeek-V2-Lite-Chat-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e155507dbcd40831a02ae30f233365aad461cb0949d97d852f7aa9e6a9f53ac
|
3 |
+
size 16702517952
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: deepseek
|
4 |
+
license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
|
5 |
+
base_model: deepseek-ai/DeepSeek-V2-Lite-Chat
|
6 |
+
tags:
|
7 |
+
- TensorBlock
|
8 |
+
- GGUF
|
9 |
+
---
|
10 |
+
|
11 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
12 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
13 |
+
</div>
|
14 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
15 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
16 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
17 |
+
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>
|
18 |
+
</p>
|
19 |
+
</div>
|
20 |
+
</div>
|
21 |
+
|
22 |
+
## deepseek-ai/DeepSeek-V2-Lite-Chat - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat).
|
25 |
+
|
26 |
+
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).
|
27 |
+
|
28 |
+
## Prompt template
|
29 |
+
|
30 |
+
```
|
31 |
+
<|begin▁of▁sentence|>{system_prompt}
|
32 |
+
|
33 |
+
User: {prompt}
|
34 |
+
|
35 |
+
Assistant:
|
36 |
+
```
|
37 |
+
|
38 |
+
## Model file specification
|
39 |
+
|
40 |
+
| Filename | Quant type | File Size | Description |
|
41 |
+
| -------- | ---------- | --------- | ----------- |
|
42 |
+
| [DeepSeek-V2-Lite-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q2_K.gguf) | Q2_K | 5.989 GB | smallest, significant quality loss - not recommended for most purposes |
|
43 |
+
| [DeepSeek-V2-Lite-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q3_K_S.gguf) | Q3_K_S | 6.973 GB | very small, high quality loss |
|
44 |
+
| [DeepSeek-V2-Lite-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q3_K_M.gguf) | Q3_K_M | 7.568 GB | very small, high quality loss |
|
45 |
+
| [DeepSeek-V2-Lite-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q3_K_L.gguf) | Q3_K_L | 7.878 GB | small, substantial quality loss |
|
46 |
+
| [DeepSeek-V2-Lite-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q4_0.gguf) | Q4_0 | 8.294 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
47 |
+
| [DeepSeek-V2-Lite-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q4_K_S.gguf) | Q4_K_S | 8.879 GB | small, greater quality loss |
|
48 |
+
| [DeepSeek-V2-Lite-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q4_K_M.gguf) | Q4_K_M | 9.653 GB | medium, balanced quality - recommended |
|
49 |
+
| [DeepSeek-V2-Lite-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q5_0.gguf) | Q5_0 | 10.097 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
50 |
+
| [DeepSeek-V2-Lite-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q5_K_S.gguf) | Q5_K_S | 10.378 GB | large, low quality loss - recommended |
|
51 |
+
| [DeepSeek-V2-Lite-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q5_K_M.gguf) | Q5_K_M | 11.037 GB | large, very low quality loss - recommended |
|
52 |
+
| [DeepSeek-V2-Lite-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q6_K.gguf) | Q6_K | 13.101 GB | very large, extremely low quality loss |
|
53 |
+
| [DeepSeek-V2-Lite-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/DeepSeek-V2-Lite-Chat-GGUF/tree/main/DeepSeek-V2-Lite-Chat-Q8_0.gguf) | Q8_0 | 15.555 GB | very large, extremely low quality loss - not recommended |
|
54 |
+
|
55 |
+
|
56 |
+
## Downloading instruction
|
57 |
+
|
58 |
+
### Command line
|
59 |
+
|
60 |
+
Firstly, install Huggingface Client
|
61 |
+
|
62 |
+
```shell
|
63 |
+
pip install -U "huggingface_hub[cli]"
|
64 |
+
```
|
65 |
+
|
66 |
+
Then, downoad the individual model file the a local directory
|
67 |
+
|
68 |
+
```shell
|
69 |
+
huggingface-cli download tensorblock/DeepSeek-V2-Lite-Chat-GGUF --include "DeepSeek-V2-Lite-Chat-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
70 |
+
```
|
71 |
+
|
72 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
73 |
+
|
74 |
+
```shell
|
75 |
+
huggingface-cli download tensorblock/DeepSeek-V2-Lite-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
76 |
+
```
|