Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- GPT-2-optim-Q2_K.gguf +3 -0
- GPT-2-optim-Q3_K_L.gguf +3 -0
- GPT-2-optim-Q3_K_M.gguf +3 -0
- GPT-2-optim-Q3_K_S.gguf +3 -0
- GPT-2-optim-Q4_0.gguf +3 -0
- GPT-2-optim-Q4_K_M.gguf +3 -0
- GPT-2-optim-Q4_K_S.gguf +3 -0
- GPT-2-optim-Q5_0.gguf +3 -0
- GPT-2-optim-Q5_K_M.gguf +3 -0
- GPT-2-optim-Q5_K_S.gguf +3 -0
- GPT-2-optim-Q6_K.gguf +3 -0
- GPT-2-optim-Q8_0.gguf +3 -0
- README.md +86 -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 |
+
GPT-2-optim-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
GPT-2-optim-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
GPT-2-optim-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
GPT-2-optim-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
GPT-2-optim-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
GPT-2-optim-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
GPT-2-optim-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
GPT-2-optim-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
GPT-2-optim-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
GPT-2-optim-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
GPT-2-optim-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
GPT-2-optim-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
GPT-2-optim-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:519ecfe18086fa528741a8038de39be00e1444d32f06b3fea2a54c068a1ec24d
|
3 |
+
size 81196608
|
GPT-2-optim-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aca0c91b11d4e845ceb114096ee0f14567f6b853d1349c4371d92164d8cc911
|
3 |
+
size 102092544
|
GPT-2-optim-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d07111c5db57300c70da558e29038da5828812251b269c4cfa4bf0fc36dfd2b
|
3 |
+
size 97668864
|
GPT-2-optim-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d3cbbb337987960b76dab9b66b75db56330cfd63ef892ba4297d8242a15d7d5
|
3 |
+
size 90148608
|
GPT-2-optim-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6695fc2ba3fe2cfcd8570912a03f687ce58973b8d673f0c136c3be2238b754b4
|
3 |
+
size 106555200
|
GPT-2-optim-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a86aa6343d813eaa11519ab9c9de4bc67c406818b9e91816838599996fc156c3
|
3 |
+
size 112858944
|
GPT-2-optim-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08af272d65658549a7b5f416ceb29daca46b3be506b72bdd94a177fba9f0daa1
|
3 |
+
size 106850112
|
GPT-2-optim-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76f8ce133fcf927fc50eb49f867d16dc9070f984499e32f41a875899a48956b2
|
3 |
+
size 121996704
|
GPT-2-optim-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80f9335f1b2fbc12cde67f8639538ca03f4f435070048d06f5feed21ece54778
|
3 |
+
size 126696864
|
GPT-2-optim-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bd8ae60dc2c07d572998cf0650b6601b709767ba72d79ef56a01793bad96c32
|
3 |
+
size 121996704
|
GPT-2-optim-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95e0775e0128142a19dcacb31438c9f851687bf22f907e54c36e35046170f50c
|
3 |
+
size 138403296
|
GPT-2-optim-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:805171129d855be70c6536153b49099e16b3af4b279462e5fcb0385608e085f8
|
3 |
+
size 177669024
|
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets: HuggingFaceFW/fineweb-edu
|
3 |
+
widget:
|
4 |
+
- example_title: Example interaction
|
5 |
+
text: During photosynthesis in green plants
|
6 |
+
inference:
|
7 |
+
parameters:
|
8 |
+
repetition_penalty: 1.3
|
9 |
+
language:
|
10 |
+
- en
|
11 |
+
library_name: transformers
|
12 |
+
license: mit
|
13 |
+
tags:
|
14 |
+
- TensorBlock
|
15 |
+
- GGUF
|
16 |
+
base_model: Alignment-Lab-AI/GPT-2-optim
|
17 |
+
---
|
18 |
+
|
19 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
20 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
21 |
+
</div>
|
22 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
23 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
24 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
25 |
+
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>
|
26 |
+
</p>
|
27 |
+
</div>
|
28 |
+
</div>
|
29 |
+
|
30 |
+
## Alignment-Lab-AI/GPT-2-optim - GGUF
|
31 |
+
|
32 |
+
This repo contains GGUF format model files for [Alignment-Lab-AI/GPT-2-optim](https://huggingface.co/Alignment-Lab-AI/GPT-2-optim).
|
33 |
+
|
34 |
+
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).
|
35 |
+
|
36 |
+
<div style="text-align: left; margin: 20px 0;">
|
37 |
+
<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;">
|
38 |
+
Run them on the TensorBlock client using your local machine ↗
|
39 |
+
</a>
|
40 |
+
</div>
|
41 |
+
|
42 |
+
## Prompt template
|
43 |
+
|
44 |
+
```
|
45 |
+
|
46 |
+
```
|
47 |
+
|
48 |
+
## Model file specification
|
49 |
+
|
50 |
+
| Filename | Quant type | File Size | Description |
|
51 |
+
| -------- | ---------- | --------- | ----------- |
|
52 |
+
| [GPT-2-optim-Q2_K.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q2_K.gguf) | Q2_K | 0.081 GB | smallest, significant quality loss - not recommended for most purposes |
|
53 |
+
| [GPT-2-optim-Q3_K_S.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q3_K_S.gguf) | Q3_K_S | 0.090 GB | very small, high quality loss |
|
54 |
+
| [GPT-2-optim-Q3_K_M.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q3_K_M.gguf) | Q3_K_M | 0.098 GB | very small, high quality loss |
|
55 |
+
| [GPT-2-optim-Q3_K_L.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q3_K_L.gguf) | Q3_K_L | 0.102 GB | small, substantial quality loss |
|
56 |
+
| [GPT-2-optim-Q4_0.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q4_0.gguf) | Q4_0 | 0.107 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
57 |
+
| [GPT-2-optim-Q4_K_S.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q4_K_S.gguf) | Q4_K_S | 0.107 GB | small, greater quality loss |
|
58 |
+
| [GPT-2-optim-Q4_K_M.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q4_K_M.gguf) | Q4_K_M | 0.113 GB | medium, balanced quality - recommended |
|
59 |
+
| [GPT-2-optim-Q5_0.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q5_0.gguf) | Q5_0 | 0.122 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
60 |
+
| [GPT-2-optim-Q5_K_S.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q5_K_S.gguf) | Q5_K_S | 0.122 GB | large, low quality loss - recommended |
|
61 |
+
| [GPT-2-optim-Q5_K_M.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q5_K_M.gguf) | Q5_K_M | 0.127 GB | large, very low quality loss - recommended |
|
62 |
+
| [GPT-2-optim-Q6_K.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q6_K.gguf) | Q6_K | 0.138 GB | very large, extremely low quality loss |
|
63 |
+
| [GPT-2-optim-Q8_0.gguf](https://huggingface.co/tensorblock/GPT-2-optim-GGUF/blob/main/GPT-2-optim-Q8_0.gguf) | Q8_0 | 0.178 GB | very large, extremely low quality loss - not recommended |
|
64 |
+
|
65 |
+
|
66 |
+
## Downloading instruction
|
67 |
+
|
68 |
+
### Command line
|
69 |
+
|
70 |
+
Firstly, install Huggingface Client
|
71 |
+
|
72 |
+
```shell
|
73 |
+
pip install -U "huggingface_hub[cli]"
|
74 |
+
```
|
75 |
+
|
76 |
+
Then, downoad the individual model file the a local directory
|
77 |
+
|
78 |
+
```shell
|
79 |
+
huggingface-cli download tensorblock/GPT-2-optim-GGUF --include "GPT-2-optim-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
80 |
+
```
|
81 |
+
|
82 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
83 |
+
|
84 |
+
```shell
|
85 |
+
huggingface-cli download tensorblock/GPT-2-optim-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
86 |
+
```
|