Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +77 -0
- llama-161M-100B-Q2_K.gguf +3 -0
- llama-161M-100B-Q3_K_L.gguf +3 -0
- llama-161M-100B-Q3_K_M.gguf +3 -0
- llama-161M-100B-Q3_K_S.gguf +3 -0
- llama-161M-100B-Q4_0.gguf +3 -0
- llama-161M-100B-Q4_K_M.gguf +3 -0
- llama-161M-100B-Q4_K_S.gguf +3 -0
- llama-161M-100B-Q5_0.gguf +3 -0
- llama-161M-100B-Q5_K_M.gguf +3 -0
- llama-161M-100B-Q5_K_S.gguf +3 -0
- llama-161M-100B-Q6_K.gguf +3 -0
- llama-161M-100B-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 |
+
llama-161M-100B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
llama-161M-100B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
llama-161M-100B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
llama-161M-100B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
llama-161M-100B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
llama-161M-100B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
llama-161M-100B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
llama-161M-100B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
llama-161M-100B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
llama-161M-100B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
llama-161M-100B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
llama-161M-100B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- TensorBlock
|
6 |
+
- GGUF
|
7 |
+
base_model: abacaj/llama-161M-100B
|
8 |
+
---
|
9 |
+
|
10 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
11 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
12 |
+
</div>
|
13 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
14 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
15 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
16 |
+
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>
|
17 |
+
</p>
|
18 |
+
</div>
|
19 |
+
</div>
|
20 |
+
|
21 |
+
## abacaj/llama-161M-100B - GGUF
|
22 |
+
|
23 |
+
This repo contains GGUF format model files for [abacaj/llama-161M-100B](https://huggingface.co/abacaj/llama-161M-100B).
|
24 |
+
|
25 |
+
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).
|
26 |
+
|
27 |
+
<div style="text-align: left; margin: 20px 0;">
|
28 |
+
<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;">
|
29 |
+
Run them on the TensorBlock client using your local machine ↗
|
30 |
+
</a>
|
31 |
+
</div>
|
32 |
+
|
33 |
+
## Prompt template
|
34 |
+
|
35 |
+
```
|
36 |
+
|
37 |
+
```
|
38 |
+
|
39 |
+
## Model file specification
|
40 |
+
|
41 |
+
| Filename | Quant type | File Size | Description |
|
42 |
+
| -------- | ---------- | --------- | ----------- |
|
43 |
+
| [llama-161M-100B-Q2_K.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q2_K.gguf) | Q2_K | 0.103 GB | smallest, significant quality loss - not recommended for most purposes |
|
44 |
+
| [llama-161M-100B-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q3_K_S.gguf) | Q3_K_S | 0.103 GB | very small, high quality loss |
|
45 |
+
| [llama-161M-100B-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q3_K_M.gguf) | Q3_K_M | 0.108 GB | very small, high quality loss |
|
46 |
+
| [llama-161M-100B-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q3_K_L.gguf) | Q3_K_L | 0.112 GB | small, substantial quality loss |
|
47 |
+
| [llama-161M-100B-Q4_0.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q4_0.gguf) | Q4_0 | 0.106 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
48 |
+
| [llama-161M-100B-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q4_K_S.gguf) | Q4_K_S | 0.120 GB | small, greater quality loss |
|
49 |
+
| [llama-161M-100B-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q4_K_M.gguf) | Q4_K_M | 0.123 GB | medium, balanced quality - recommended |
|
50 |
+
| [llama-161M-100B-Q5_0.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q5_0.gguf) | Q5_0 | 0.123 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
51 |
+
| [llama-161M-100B-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q5_K_S.gguf) | Q5_K_S | 0.130 GB | large, low quality loss - recommended |
|
52 |
+
| [llama-161M-100B-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q5_K_M.gguf) | Q5_K_M | 0.132 GB | large, very low quality loss - recommended |
|
53 |
+
| [llama-161M-100B-Q6_K.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q6_K.gguf) | Q6_K | 0.166 GB | very large, extremely low quality loss |
|
54 |
+
| [llama-161M-100B-Q8_0.gguf](https://huggingface.co/tensorblock/llama-161M-100B-GGUF/blob/main/llama-161M-100B-Q8_0.gguf) | Q8_0 | 0.173 GB | very large, extremely low quality loss - not recommended |
|
55 |
+
|
56 |
+
|
57 |
+
## Downloading instruction
|
58 |
+
|
59 |
+
### Command line
|
60 |
+
|
61 |
+
Firstly, install Huggingface Client
|
62 |
+
|
63 |
+
```shell
|
64 |
+
pip install -U "huggingface_hub[cli]"
|
65 |
+
```
|
66 |
+
|
67 |
+
Then, downoad the individual model file the a local directory
|
68 |
+
|
69 |
+
```shell
|
70 |
+
huggingface-cli download tensorblock/llama-161M-100B-GGUF --include "llama-161M-100B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
71 |
+
```
|
72 |
+
|
73 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
74 |
+
|
75 |
+
```shell
|
76 |
+
huggingface-cli download tensorblock/llama-161M-100B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
77 |
+
```
|
llama-161M-100B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ef9d1bcd04c0569b0919190474da82a31365e2f2a9981635e74727688f637fe
|
3 |
+
size 102763648
|
llama-161M-100B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c28177d5c34770145273d33110664535cdbb32963c4a6b784b33166271541b1
|
3 |
+
size 111752320
|
llama-161M-100B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14dc27cfe9869dabe26c57b5e497f44d02c7a7080c37729f0effe5677ab9b369
|
3 |
+
size 107637888
|
llama-161M-100B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d32f08ebbb29f454fd6e0a9f63d36730b8f9d70607fa788408e7710731c2cdf1
|
3 |
+
size 102591616
|
llama-161M-100B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d389ca0fd0d2c7a1e1af513a9885d775fa6ed142789c6461699b8d6b0104d02
|
3 |
+
size 106247296
|
llama-161M-100B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a921873028afa2450c318a225ba6a0b1890bcb23344e898e737a278f3a017037
|
3 |
+
size 123271296
|
llama-161M-100B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f0f3d02e35632f33d8f3ac94987fe4bc229f7a62f25f73288464262a63cb1b5
|
3 |
+
size 119780480
|
llama-161M-100B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75451bafc235398d0a58f393f97805ff5bb8bdae2e9a47fa6b8f4779027806d2
|
3 |
+
size 122905728
|
llama-161M-100B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37b7ee5516e8370aa1f6b90454aa3bfb0ec9baf1d3c461746604f16316c2f984
|
3 |
+
size 131557504
|
llama-161M-100B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f38f28b851a2e31abc921323d63aba14355f92bb09e276ced94983e5b2503048
|
3 |
+
size 129514624
|
llama-161M-100B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb6f3db572af2cf52751d6169e625831c12de4d3f39faad2891784cfc122aca6
|
3 |
+
size 166214784
|
llama-161M-100B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b8f232fae497072716cabb13aaeb313e1a17eed5eb390267bfc6da8d740b8d9
|
3 |
+
size 172881024
|