Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q2_K.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_L.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_M.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_S.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_0.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_M.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_S.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_0.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_M.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_S.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q6_K.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-plus-Swallow-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 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfc5ba0de8066248d3a3205e1380648edfa084a0f517f7e69840e2aba3e04c84
|
3 |
+
size 3179131712
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef172d42ace6f794ea0d620c3a99a9037b48ddcb12d6f0510119fb2bd7d677d7
|
3 |
+
size 4321956672
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1cc96f4f05cb659dffcde341f75c51a92ef55b55cd3aec3079471ab897fd8be
|
3 |
+
size 4018918208
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1eb34d3fe225ca130d2386677f45b7b914f0f9a2a0cb3a2721091e7f18f1ed02
|
3 |
+
size 3664499520
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a35390f818aa9d0cd3795f6839b337fdbb75a461918d309c70809bf00b91cc56
|
3 |
+
size 4661211968
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:754460924cadea174fbae43b5ccec66f6a75d8d60b60b5afc597eb6bf28b9a64
|
3 |
+
size 4920734528
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13d6a70c548e932308a0ef56cb4997cab6fdb331d2bf87d5bef361f3367e8d6d
|
3 |
+
size 4692669248
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14015fabbc1d2ff5532a6850cc7330335b8c52e028ddd8de25c2ed6f26f6ec81
|
3 |
+
size 5599294272
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9002a7a8f88594557711308a1c59ece476b25e4c57e3165ccff03360679d62e
|
3 |
+
size 5732987712
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:991b8c9c3b5c79ada9f9719e99addf0254a6b4feb7371332b179d9f253cb41ed
|
3 |
+
size 5599294272
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53c2beff764c7461ca822ae3fe25465673faada82d238fbb997d1144297d2045
|
3 |
+
size 6596006720
|
Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff8fe37fa414ce226a2822873c74307d0f502c3dd1e332224a252d2dab99edce
|
3 |
+
size 8540771136
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3.1
|
3 |
+
language:
|
4 |
+
- ja
|
5 |
+
tags:
|
6 |
+
- TensorBlock
|
7 |
+
- GGUF
|
8 |
+
base_model: aixsatoshi/Meta-Llama-3.1-8B-Instruct-plus-Swallow
|
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 |
+
## aixsatoshi/Meta-Llama-3.1-8B-Instruct-plus-Swallow - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [aixsatoshi/Meta-Llama-3.1-8B-Instruct-plus-Swallow](https://huggingface.co/aixsatoshi/Meta-Llama-3.1-8B-Instruct-plus-Swallow).
|
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_text|><|start_header_id|>system<|end_header_id|>
|
32 |
+
|
33 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
34 |
+
|
35 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
36 |
+
```
|
37 |
+
|
38 |
+
## Model file specification
|
39 |
+
|
40 |
+
| Filename | Quant type | File Size | Description |
|
41 |
+
| -------- | ---------- | --------- | ----------- |
|
42 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q2_K.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
43 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_S.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
44 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_M.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
45 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_L.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
46 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_0.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
47 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_S.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
48 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_M.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
49 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_0.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
50 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_S.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
51 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_M.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
52 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q6_K.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
53 |
+
| [Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q8_0.gguf](https://huggingface.co/tensorblock/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF/tree/main/Meta-Llama-3.1-8B-Instruct-plus-Swallow-Q8_0.gguf) | Q8_0 | 7.954 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/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF --include "Meta-Llama-3.1-8B-Instruct-plus-Swallow-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/Meta-Llama-3.1-8B-Instruct-plus-Swallow-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
76 |
+
```
|