Upload folder using huggingface_hub
Browse files- .gitattributes +15 -0
- Llama-SEA-LION-v3-70B-IT-Q2_K.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q3_K_L.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q3_K_M.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q3_K_S.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q4_0.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q4_K_M.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q4_K_S.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q5_0.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q5_K_M.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q5_K_S.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q6_K/Llama-SEA-LION-v3-70B-IT-Q6_K-00001-of-00002.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q6_K/Llama-SEA-LION-v3-70B-IT-Q6_K-00002-of-00002.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00001-of-00003.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00002-of-00003.gguf +3 -0
- Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00003-of-00003.gguf +3 -0
- README.md +136 -0
.gitattributes
CHANGED
@@ -33,3 +33,18 @@ 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-SEA-LION-v3-70B-IT-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-SEA-LION-v3-70B-IT-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-SEA-LION-v3-70B-IT-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-SEA-LION-v3-70B-IT-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-SEA-LION-v3-70B-IT-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-SEA-LION-v3-70B-IT-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-SEA-LION-v3-70B-IT-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-SEA-LION-v3-70B-IT-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-SEA-LION-v3-70B-IT-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-SEA-LION-v3-70B-IT-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-SEA-LION-v3-70B-IT-Q6_K/Llama-SEA-LION-v3-70B-IT-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-SEA-LION-v3-70B-IT-Q6_K/Llama-SEA-LION-v3-70B-IT-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
49 |
+
Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
50 |
+
Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-SEA-LION-v3-70B-IT-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:accb790bf0d1a3a65780b31fc29bce2e38e192ec568587def2ab3f26b88abe92
|
3 |
+
size 26375113408
|
Llama-SEA-LION-v3-70B-IT-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a75cd05ccfa88fe622a530c47e1b19971a19de7b982e732b27eb037980ce9935
|
3 |
+
size 37140597440
|
Llama-SEA-LION-v3-70B-IT-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a2227c52328bac22de91f678ea1ce2cce8cb216fd5f73b96aea20898c462e35
|
3 |
+
size 34267499200
|
Llama-SEA-LION-v3-70B-IT-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0592a84ad5a82f2831b36ec604df0dc3998edb20468b68dab85a4b919f58d9f
|
3 |
+
size 30912056000
|
Llama-SEA-LION-v3-70B-IT-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:253c5871f2cb212c32b6eb441f91fe579c06049b07b011733c2eb21268111ae8
|
3 |
+
size 39969737408
|
Llama-SEA-LION-v3-70B-IT-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72b7155328be9bea3554a7b40827f4d75b9e0ea14f4b81e929b0cf446a7c6b21
|
3 |
+
size 42520398528
|
Llama-SEA-LION-v3-70B-IT-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0ceff6807152abce33097180eeae771e0fe46345b5caaefb61935cd80347b5d
|
3 |
+
size 40347224768
|
Llama-SEA-LION-v3-70B-IT-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbf8c1911878a3a9b7267315b3ea34a099af6dcd730c32926549e892e60877dd
|
3 |
+
size 48657451712
|
Llama-SEA-LION-v3-70B-IT-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1e499744c1d3f3af4f8c0afa43d9d9e8f8f81aee4695a255c9d418703b91b4a
|
3 |
+
size 49949821632
|
Llama-SEA-LION-v3-70B-IT-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:291f24ae8eae25df156f3ac1c80bbe5f7a1adca7fdbd4fc50417dea51a936766
|
3 |
+
size 48657451712
|
Llama-SEA-LION-v3-70B-IT-Q6_K/Llama-SEA-LION-v3-70B-IT-Q6_K-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:246c2030594d2e49742ff39d7ea2cc749cf85b99bea27a34e6a8742107629a80
|
3 |
+
size 34847475424
|
Llama-SEA-LION-v3-70B-IT-Q6_K/Llama-SEA-LION-v3-70B-IT-Q6_K-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a3cb7428253766ab7ebf4ae536546abec4c29412a5d6d3f0531522973b3f79d
|
3 |
+
size 23040672928
|
Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00001-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:738d3c4f3a6b4cbb2150d3c3d2e6162ab85d366206cd497004594b630981eb75
|
3 |
+
size 34980015872
|
Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00002-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f18dbf2c0a0a5a26643291006d70cd9d11c746bf72714d3ba901b1d69312030
|
3 |
+
size 34949976384
|
Llama-SEA-LION-v3-70B-IT-Q8_0/Llama-SEA-LION-v3-70B-IT-Q8_0-00003-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5fccacdc360aafac8a0cffc7f94f4e3a959fbeb576e51ed50a1cf5db033b9e2
|
3 |
+
size 5045062560
|
README.md
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
base_model: aisingapore/Llama-SEA-LION-v3-70B-IT
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
- zh
|
8 |
+
- vi
|
9 |
+
- id
|
10 |
+
- th
|
11 |
+
- fil
|
12 |
+
- ta
|
13 |
+
- ms
|
14 |
+
- km
|
15 |
+
- lo
|
16 |
+
- my
|
17 |
+
- jv
|
18 |
+
- su
|
19 |
+
license: llama3.1
|
20 |
+
base_model_relation: finetune
|
21 |
+
tags:
|
22 |
+
- TensorBlock
|
23 |
+
- GGUF
|
24 |
+
---
|
25 |
+
|
26 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
27 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
28 |
+
</div>
|
29 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
30 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
31 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
32 |
+
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>
|
33 |
+
</p>
|
34 |
+
</div>
|
35 |
+
</div>
|
36 |
+
|
37 |
+
## aisingapore/Llama-SEA-LION-v3-70B-IT - GGUF
|
38 |
+
|
39 |
+
This repo contains GGUF format model files for [aisingapore/Llama-SEA-LION-v3-70B-IT](https://huggingface.co/aisingapore/Llama-SEA-LION-v3-70B-IT).
|
40 |
+
|
41 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985).
|
42 |
+
|
43 |
+
## Our projects
|
44 |
+
<table border="1" cellspacing="0" cellpadding="10">
|
45 |
+
<tr>
|
46 |
+
<th style="font-size: 25px;">Awesome MCP Servers</th>
|
47 |
+
<th style="font-size: 25px;">TensorBlock Studio</th>
|
48 |
+
</tr>
|
49 |
+
<tr>
|
50 |
+
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
|
51 |
+
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
|
52 |
+
</tr>
|
53 |
+
<tr>
|
54 |
+
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
|
55 |
+
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
|
56 |
+
</tr>
|
57 |
+
<tr>
|
58 |
+
<th>
|
59 |
+
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
|
60 |
+
display: inline-block;
|
61 |
+
padding: 8px 16px;
|
62 |
+
background-color: #FF7F50;
|
63 |
+
color: white;
|
64 |
+
text-decoration: none;
|
65 |
+
border-radius: 6px;
|
66 |
+
font-weight: bold;
|
67 |
+
font-family: sans-serif;
|
68 |
+
">π See what we built π</a>
|
69 |
+
</th>
|
70 |
+
<th>
|
71 |
+
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
|
72 |
+
display: inline-block;
|
73 |
+
padding: 8px 16px;
|
74 |
+
background-color: #FF7F50;
|
75 |
+
color: white;
|
76 |
+
text-decoration: none;
|
77 |
+
border-radius: 6px;
|
78 |
+
font-weight: bold;
|
79 |
+
font-family: sans-serif;
|
80 |
+
">π See what we built π</a>
|
81 |
+
</th>
|
82 |
+
</tr>
|
83 |
+
</table>
|
84 |
+
|
85 |
+
## Prompt template
|
86 |
+
|
87 |
+
```
|
88 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
89 |
+
|
90 |
+
Cutting Knowledge Date: December 2023
|
91 |
+
Today Date: 26 Jul 2024
|
92 |
+
|
93 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
94 |
+
|
95 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
96 |
+
```
|
97 |
+
|
98 |
+
## Model file specification
|
99 |
+
|
100 |
+
| Filename | Quant type | File Size | Description |
|
101 |
+
| -------- | ---------- | --------- | ----------- |
|
102 |
+
| [Llama-SEA-LION-v3-70B-IT-Q2_K.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
|
103 |
+
| [Llama-SEA-LION-v3-70B-IT-Q3_K_S.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
|
104 |
+
| [Llama-SEA-LION-v3-70B-IT-Q3_K_M.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
|
105 |
+
| [Llama-SEA-LION-v3-70B-IT-Q3_K_L.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
|
106 |
+
| [Llama-SEA-LION-v3-70B-IT-Q4_0.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
107 |
+
| [Llama-SEA-LION-v3-70B-IT-Q4_K_S.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
|
108 |
+
| [Llama-SEA-LION-v3-70B-IT-Q4_K_M.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
|
109 |
+
| [Llama-SEA-LION-v3-70B-IT-Q5_0.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
110 |
+
| [Llama-SEA-LION-v3-70B-IT-Q5_K_S.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
|
111 |
+
| [Llama-SEA-LION-v3-70B-IT-Q5_K_M.gguf](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
|
112 |
+
| [Llama-SEA-LION-v3-70B-IT-Q6_K](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
|
113 |
+
| [Llama-SEA-LION-v3-70B-IT-Q8_0](https://huggingface.co/tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF/blob/main/Llama-SEA-LION-v3-70B-IT-Q8_0) | Q8_0 | 74.975 GB | very large, extremely low quality loss - not recommended |
|
114 |
+
|
115 |
+
|
116 |
+
## Downloading instruction
|
117 |
+
|
118 |
+
### Command line
|
119 |
+
|
120 |
+
Firstly, install Huggingface Client
|
121 |
+
|
122 |
+
```shell
|
123 |
+
pip install -U "huggingface_hub[cli]"
|
124 |
+
```
|
125 |
+
|
126 |
+
Then, downoad the individual model file the a local directory
|
127 |
+
|
128 |
+
```shell
|
129 |
+
huggingface-cli download tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF --include "Llama-SEA-LION-v3-70B-IT-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
130 |
+
```
|
131 |
+
|
132 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
133 |
+
|
134 |
+
```shell
|
135 |
+
huggingface-cli download tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
136 |
+
```
|