Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +88 -0
- distilgpt2-Q2_K.gguf +3 -0
- distilgpt2-Q3_K_L.gguf +3 -0
- distilgpt2-Q3_K_M.gguf +3 -0
- distilgpt2-Q3_K_S.gguf +3 -0
- distilgpt2-Q4_0.gguf +3 -0
- distilgpt2-Q4_K_M.gguf +3 -0
- distilgpt2-Q4_K_S.gguf +3 -0
- distilgpt2-Q5_0.gguf +3 -0
- distilgpt2-Q5_K_M.gguf +3 -0
- distilgpt2-Q5_K_S.gguf +3 -0
- distilgpt2-Q6_K.gguf +3 -0
- distilgpt2-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 |
+
distilgpt2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
distilgpt2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
distilgpt2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
distilgpt2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
distilgpt2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
distilgpt2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
distilgpt2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
distilgpt2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
distilgpt2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
distilgpt2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
distilgpt2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
distilgpt2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
tags:
|
4 |
+
- exbert
|
5 |
+
- TensorBlock
|
6 |
+
- GGUF
|
7 |
+
license: apache-2.0
|
8 |
+
datasets:
|
9 |
+
- openwebtext
|
10 |
+
co2_eq_emissions: 149200
|
11 |
+
base_model: distilbert/distilgpt2
|
12 |
+
model-index:
|
13 |
+
- name: distilgpt2
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
type: text-generation
|
17 |
+
name: Text Generation
|
18 |
+
dataset:
|
19 |
+
name: WikiText-103
|
20 |
+
type: wikitext
|
21 |
+
metrics:
|
22 |
+
- type: perplexity
|
23 |
+
value: 21.1
|
24 |
+
name: Perplexity
|
25 |
+
---
|
26 |
+
|
27 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
28 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
29 |
+
</div>
|
30 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
31 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
32 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
33 |
+
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>
|
34 |
+
</p>
|
35 |
+
</div>
|
36 |
+
</div>
|
37 |
+
|
38 |
+
## distilbert/distilgpt2 - GGUF
|
39 |
+
|
40 |
+
This repo contains GGUF format model files for [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2).
|
41 |
+
|
42 |
+
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).
|
43 |
+
|
44 |
+
## Prompt template
|
45 |
+
|
46 |
+
```
|
47 |
+
|
48 |
+
```
|
49 |
+
|
50 |
+
## Model file specification
|
51 |
+
|
52 |
+
| Filename | Quant type | File Size | Description |
|
53 |
+
| -------- | ---------- | --------- | ----------- |
|
54 |
+
| [distilgpt2-Q2_K.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q2_K.gguf) | Q2_K | 0.061 GB | smallest, significant quality loss - not recommended for most purposes |
|
55 |
+
| [distilgpt2-Q3_K_S.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q3_K_S.gguf) | Q3_K_S | 0.067 GB | very small, high quality loss |
|
56 |
+
| [distilgpt2-Q3_K_M.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q3_K_M.gguf) | Q3_K_M | 0.070 GB | very small, high quality loss |
|
57 |
+
| [distilgpt2-Q3_K_L.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q3_K_L.gguf) | Q3_K_L | 0.072 GB | small, substantial quality loss |
|
58 |
+
| [distilgpt2-Q4_0.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q4_0.gguf) | Q4_0 | 0.077 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
59 |
+
| [distilgpt2-Q4_K_S.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q4_K_S.gguf) | Q4_K_S | 0.077 GB | small, greater quality loss |
|
60 |
+
| [distilgpt2-Q4_K_M.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q4_K_M.gguf) | Q4_K_M | 0.079 GB | medium, balanced quality - recommended |
|
61 |
+
| [distilgpt2-Q5_0.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q5_0.gguf) | Q5_0 | 0.086 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
62 |
+
| [distilgpt2-Q5_K_S.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q5_K_S.gguf) | Q5_K_S | 0.086 GB | large, low quality loss - recommended |
|
63 |
+
| [distilgpt2-Q5_K_M.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q5_K_M.gguf) | Q5_K_M | 0.088 GB | large, very low quality loss - recommended |
|
64 |
+
| [distilgpt2-Q6_K.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q6_K.gguf) | Q6_K | 0.096 GB | very large, extremely low quality loss |
|
65 |
+
| [distilgpt2-Q8_0.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q8_0.gguf) | Q8_0 | 0.123 GB | very large, extremely low quality loss - not recommended |
|
66 |
+
|
67 |
+
|
68 |
+
## Downloading instruction
|
69 |
+
|
70 |
+
### Command line
|
71 |
+
|
72 |
+
Firstly, install Huggingface Client
|
73 |
+
|
74 |
+
```shell
|
75 |
+
pip install -U "huggingface_hub[cli]"
|
76 |
+
```
|
77 |
+
|
78 |
+
Then, downoad the individual model file the a local directory
|
79 |
+
|
80 |
+
```shell
|
81 |
+
huggingface-cli download tensorblock/distilgpt2-GGUF --include "distilgpt2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
82 |
+
```
|
83 |
+
|
84 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
85 |
+
|
86 |
+
```shell
|
87 |
+
huggingface-cli download tensorblock/distilgpt2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
88 |
+
```
|
distilgpt2-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:700846bf963d4a188dd1ab3d7f19d0171297cc1e790c40d88a64f7e0631fe65c
|
3 |
+
size 65221280
|
distilgpt2-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f72f5fd5e0e58833836ad14b539c0e3ec66935f24600e13fdb1e8aa120bd5e7
|
3 |
+
size 77629280
|
distilgpt2-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14475df7d0afce621c049630a40b6fbe6eef8a05b009e8b0ec41ffedcc2f59e5
|
3 |
+
size 75417440
|
distilgpt2-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d04e20f0295ed10672e6f326161abae1eaa22d52354b95b28933545ef85ec8
|
3 |
+
size 71657312
|
distilgpt2-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e364012b3da695fd0bf7793bf589f9b1157e42730f04a9266fb381618ffff6e0
|
3 |
+
size 82423712
|
distilgpt2-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482de941a6f0c3a4533faba6981fc15318e0212f70761d778cc0e3e63e42609f
|
3 |
+
size 84967328
|
distilgpt2-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4c8dc817a453df6b69b0c579f15021ec8caa93184082e75996d019fe0ba81dc
|
3 |
+
size 82423712
|
distilgpt2-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2021615ab82f9a9b5fd805d784c06d1faa4d978c451bb30954699f4357986ba7
|
3 |
+
size 92556800
|
distilgpt2-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:941cd80a64804d24a7bcbe83a0abb3d100576f4f5b2da6479719800e177236b9
|
3 |
+
size 94593536
|
distilgpt2-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c62e2721a4b3bd6b38b55e93f5039395c5ccb5e46a190827ed3435b867c19c2a
|
3 |
+
size 92556800
|
distilgpt2-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebd57742361bcc77e1f53e8752fc9970ccf6e0c39f51cb50b6066d26a2973ce6
|
3 |
+
size 103323200
|
distilgpt2-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:407f73e88c98d72fbdc8737a0de6947752b078bb8adb884674cadb40a361e06c
|
3 |
+
size 132303872
|