Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Llama-3-Smaug-8B-Q2_K.gguf +3 -0
- Llama-3-Smaug-8B-Q3_K_L.gguf +3 -0
- Llama-3-Smaug-8B-Q3_K_M.gguf +3 -0
- Llama-3-Smaug-8B-Q3_K_S.gguf +3 -0
- Llama-3-Smaug-8B-Q4_0.gguf +3 -0
- Llama-3-Smaug-8B-Q4_K_M.gguf +3 -0
- Llama-3-Smaug-8B-Q4_K_S.gguf +3 -0
- Llama-3-Smaug-8B-Q5_0.gguf +3 -0
- Llama-3-Smaug-8B-Q5_K_M.gguf +3 -0
- Llama-3-Smaug-8B-Q5_K_S.gguf +3 -0
- Llama-3-Smaug-8B-Q6_K.gguf +3 -0
- Llama-3-Smaug-8B-Q8_0.gguf +3 -0
- README.md +80 -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-3-Smaug-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-3-Smaug-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-3-Smaug-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-3-Smaug-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-3-Smaug-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-3-Smaug-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-3-Smaug-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-3-Smaug-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-3-Smaug-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-3-Smaug-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-3-Smaug-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-3-Smaug-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-3-Smaug-8B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdc9cf58779ea35adbdd91ec2d9f0fc7c0011e241ae9c21a3c74509a22a31a32
|
3 |
+
size 3179131584
|
Llama-3-Smaug-8B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30521aa96a6f1c99b90b05642c8ac3a4f6088454f265602e52e98c9610be3c01
|
3 |
+
size 4321956544
|
Llama-3-Smaug-8B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b018afcce10193deb830d700fddcded397879e5ffe235624ddefe8a77f7ec0b8
|
3 |
+
size 4018918080
|
Llama-3-Smaug-8B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dff91f78fabcdf39cbf8f349e8498d1a816682ea9ece68c0ea44ec00c894337
|
3 |
+
size 3664499392
|
Llama-3-Smaug-8B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2e93a66b1fed28cc843dd04b0bda8b64dd9b4da527e11f71871254405ebe55a
|
3 |
+
size 4661211840
|
Llama-3-Smaug-8B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:317635fe6dcab7321ae9182aef545b801ca2db957af237c49606e42b575ecffc
|
3 |
+
size 4920734400
|
Llama-3-Smaug-8B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a00c50671170d9abce125f39caa940cd853337b8d0c42907e6a09143faa95109
|
3 |
+
size 4692669120
|
Llama-3-Smaug-8B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:590a002126132edabae0d392bf014873473cf04561363c661db9cc910f609b8d
|
3 |
+
size 5599294144
|
Llama-3-Smaug-8B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e38dbe9c3dbe729e78afa1d06a20a488c95b8db29b9a48f15cbcd8211137483
|
3 |
+
size 5732987584
|
Llama-3-Smaug-8B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:557916e29b07c5a6eac8dec0ac8b2ba9e920f751397dec4f275f1e3c5a3b658a
|
3 |
+
size 5599294144
|
Llama-3-Smaug-8B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:667aed96ca85a49dc72d70f9606742662274217155fa3fdf4fd7047e221fb858
|
3 |
+
size 6596006592
|
Llama-3-Smaug-8B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ec6425026737c11719854afee480f9562bcf6ca326f07fd11688ad05e4f2762
|
3 |
+
size 8540771008
|
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: llama2
|
4 |
+
datasets:
|
5 |
+
- aqua_rat
|
6 |
+
- microsoft/orca-math-word-problems-200k
|
7 |
+
- m-a-p/CodeFeedback-Filtered-Instruction
|
8 |
+
- anon8231489123/ShareGPT_Vicuna_unfiltered
|
9 |
+
tags:
|
10 |
+
- TensorBlock
|
11 |
+
- GGUF
|
12 |
+
base_model: abacusai/Llama-3-Smaug-8B
|
13 |
+
---
|
14 |
+
|
15 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
16 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
17 |
+
</div>
|
18 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
19 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
20 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
21 |
+
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>
|
22 |
+
</p>
|
23 |
+
</div>
|
24 |
+
</div>
|
25 |
+
|
26 |
+
## abacusai/Llama-3-Smaug-8B - GGUF
|
27 |
+
|
28 |
+
This repo contains GGUF format model files for [abacusai/Llama-3-Smaug-8B](https://huggingface.co/abacusai/Llama-3-Smaug-8B).
|
29 |
+
|
30 |
+
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).
|
31 |
+
|
32 |
+
## Prompt template
|
33 |
+
|
34 |
+
```
|
35 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
36 |
+
|
37 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
38 |
+
|
39 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
40 |
+
```
|
41 |
+
|
42 |
+
## Model file specification
|
43 |
+
|
44 |
+
| Filename | Quant type | File Size | Description |
|
45 |
+
| -------- | ---------- | --------- | ----------- |
|
46 |
+
| [Llama-3-Smaug-8B-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
47 |
+
| [Llama-3-Smaug-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
48 |
+
| [Llama-3-Smaug-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
49 |
+
| [Llama-3-Smaug-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
50 |
+
| [Llama-3-Smaug-8B-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
51 |
+
| [Llama-3-Smaug-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
52 |
+
| [Llama-3-Smaug-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
53 |
+
| [Llama-3-Smaug-8B-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
54 |
+
| [Llama-3-Smaug-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
55 |
+
| [Llama-3-Smaug-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
56 |
+
| [Llama-3-Smaug-8B-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
57 |
+
| [Llama-3-Smaug-8B-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-Smaug-8B-GGUF/tree/main/Llama-3-Smaug-8B-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
58 |
+
|
59 |
+
|
60 |
+
## Downloading instruction
|
61 |
+
|
62 |
+
### Command line
|
63 |
+
|
64 |
+
Firstly, install Huggingface Client
|
65 |
+
|
66 |
+
```shell
|
67 |
+
pip install -U "huggingface_hub[cli]"
|
68 |
+
```
|
69 |
+
|
70 |
+
Then, downoad the individual model file the a local directory
|
71 |
+
|
72 |
+
```shell
|
73 |
+
huggingface-cli download tensorblock/Llama-3-Smaug-8B-GGUF --include "Llama-3-Smaug-8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
74 |
+
```
|
75 |
+
|
76 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
77 |
+
|
78 |
+
```shell
|
79 |
+
huggingface-cli download tensorblock/Llama-3-Smaug-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
80 |
+
```
|