Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Nusantara-0.8b-Indo-Chat-Q2_K.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q3_K_L.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q3_K_M.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q3_K_S.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q4_0.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q4_K_M.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q4_K_S.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q5_0.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q5_K_M.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q5_K_S.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q6_K.gguf +3 -0
- Nusantara-0.8b-Indo-Chat-Q8_0.gguf +3 -0
- README.md +134 -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 |
+
Nusantara-0.8b-Indo-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Nusantara-0.8b-Indo-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Nusantara-0.8b-Indo-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Nusantara-0.8b-Indo-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Nusantara-0.8b-Indo-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Nusantara-0.8b-Indo-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Nusantara-0.8b-Indo-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Nusantara-0.8b-Indo-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Nusantara-0.8b-Indo-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Nusantara-0.8b-Indo-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Nusantara-0.8b-Indo-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Nusantara-0.8b-Indo-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Nusantara-0.8b-Indo-Chat-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7118e1f8ffdd8d44432d91da2f29b925beee5c938047b392903834a22e38be38
|
3 |
+
size 374282432
|
Nusantara-0.8b-Indo-Chat-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cfdb0103a3b265c68f8eabae430cc9fa418f8f915ea67baa3432265e06db767
|
3 |
+
size 473396416
|
Nusantara-0.8b-Indo-Chat-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:098291f70ae6a5796522b330b36b324dc7fce8b77c1aa935fa3264df3e792dad
|
3 |
+
size 449475776
|
Nusantara-0.8b-Indo-Chat-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba80753b3443914a8cf216a5e529424aa8f76b66a93747ed4f8158819a0361e2
|
3 |
+
size 422032576
|
Nusantara-0.8b-Indo-Chat-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8deb7472654ef324268c90140a12ffb4726f9692f578a86609d5d6575dfefd6
|
3 |
+
size 510935232
|
Nusantara-0.8b-Indo-Chat-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43b6a3f47f20286c8f5fc6939d300d50bfd75f09c613ce2bf8108c8281948c65
|
3 |
+
size 531210432
|
Nusantara-0.8b-Indo-Chat-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87dac0bf20b19bdebd5414d4906c775bf4a45df4e8750f2a299672b5bc69f50b
|
3 |
+
size 513261760
|
Nusantara-0.8b-Indo-Chat-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99ad4252c88aaf2e3301666abba0cb97a6178910673063377d60a186f4f7c2a6
|
3 |
+
size 594608320
|
Nusantara-0.8b-Indo-Chat-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612a0a78da830ea59b8dbaf43eb21782b213458d7b4b0b59dce3d4db0f57d790
|
3 |
+
size 605053120
|
Nusantara-0.8b-Indo-Chat-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:411f2a053f1cc35e562b2b93513ac30627949f169e8ce3029969125a25547374
|
3 |
+
size 594608320
|
Nusantara-0.8b-Indo-Chat-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c90f8d39890ccde779e4455bd252787f2014e90bb2728b0807a8fce456fd2aba
|
3 |
+
size 683510976
|
Nusantara-0.8b-Indo-Chat-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70981ffa0b74c35db9b0f2d683c9b4778a1e7aa146c4879443315e0305cc65a5
|
3 |
+
size 883307712
|
README.md
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
widget:
|
4 |
+
- messages:
|
5 |
+
- role: system
|
6 |
+
content: Anda adalah seorang konselor karir. User akan memberi Anda seorang individu
|
7 |
+
mencari bimbingan dalam kehidupan profesional mereka, dan tugas Anda adalah
|
8 |
+
membantu mereka dalam menentukan karir apa yang paling cocok bagi mereka berdasarkan
|
9 |
+
keterampilan mereka, minat, dan pengalaman. Anda juga harus melakukan penelitian
|
10 |
+
terhadap berbagai hal tersebut pilihan yang tersedia, jelaskan tren pasar kerja
|
11 |
+
di berbagai industri, Dan saran tentang kualifikasi mana yang akan bermanfaat
|
12 |
+
untuk mengejar bidang tertentu.
|
13 |
+
- role: user
|
14 |
+
content: Hellow!
|
15 |
+
- role: assistant
|
16 |
+
content: Hai! Apa yang bisa saya bantu?
|
17 |
+
- role: user
|
18 |
+
content: Saya tertarik untuk mengembangkan karir di bidang rekayasa perangkat
|
19 |
+
lunak. Apa Anda mau merekomendasikan saya untuk melakukannya?
|
20 |
+
- messages:
|
21 |
+
- role: system
|
22 |
+
content: Anda adalah asisten yang berpengetahuan luas. Bantu user sebanyak yang
|
23 |
+
Anda bisa.
|
24 |
+
- role: user
|
25 |
+
content: Bagaimana caranya menjadi lebih sehat?
|
26 |
+
- messages:
|
27 |
+
- role: system
|
28 |
+
content: Anda adalah asisten yang membantu dan memberikan tanggapan yang cerdas.
|
29 |
+
- role: user
|
30 |
+
content: Haloooo Bund!
|
31 |
+
- role: assistant
|
32 |
+
content: Halo! Apa yang bisa saya bantu?
|
33 |
+
- role: user
|
34 |
+
content: Saya perlu membangun situs web sederhana. Di mana saya harus mulai belajar
|
35 |
+
tentang pengembangan web?
|
36 |
+
- messages:
|
37 |
+
- role: system
|
38 |
+
content: Anda adalah asisten yang sangat kreatif. Pengguna akan memberi Anda tugas,
|
39 |
+
yang harus Anda selesaikan dengan seluruh pengetahuan Anda.
|
40 |
+
- role: user
|
41 |
+
content: Tulis latar belakang cerita game RPG tentang penyihir dan naga di dunia
|
42 |
+
fiksi ilmiah.
|
43 |
+
inference:
|
44 |
+
parameters:
|
45 |
+
max_new_tokens: 128
|
46 |
+
penalty_alpha: 0.5
|
47 |
+
top_k: 4
|
48 |
+
pipeline_tag: text-generation
|
49 |
+
tags:
|
50 |
+
- conversational
|
51 |
+
- convAI
|
52 |
+
- TensorBlock
|
53 |
+
- GGUF
|
54 |
+
license: apache-2.0
|
55 |
+
language:
|
56 |
+
- id
|
57 |
+
- en
|
58 |
+
datasets:
|
59 |
+
- FreedomIntelligence/evol-instruct-indonesian
|
60 |
+
base_model: kalisai/Nusantara-0.8b-Indo-Chat
|
61 |
+
---
|
62 |
+
|
63 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
64 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
65 |
+
</div>
|
66 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
67 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
68 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
69 |
+
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>
|
70 |
+
</p>
|
71 |
+
</div>
|
72 |
+
</div>
|
73 |
+
|
74 |
+
## kalisai/Nusantara-0.8b-Indo-Chat - GGUF
|
75 |
+
|
76 |
+
This repo contains GGUF format model files for [kalisai/Nusantara-0.8b-Indo-Chat](https://huggingface.co/kalisai/Nusantara-0.8b-Indo-Chat).
|
77 |
+
|
78 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
79 |
+
|
80 |
+
<div style="text-align: left; margin: 20px 0;">
|
81 |
+
<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;">
|
82 |
+
Run them on the TensorBlock client using your local machine ↗
|
83 |
+
</a>
|
84 |
+
</div>
|
85 |
+
|
86 |
+
## Prompt template
|
87 |
+
|
88 |
+
```
|
89 |
+
<|im_start|>system
|
90 |
+
{system_prompt}<|im_end|>
|
91 |
+
<|im_start|>user
|
92 |
+
{prompt}<|im_end|>
|
93 |
+
<|im_start|>assistant
|
94 |
+
```
|
95 |
+
|
96 |
+
## Model file specification
|
97 |
+
|
98 |
+
| Filename | Quant type | File Size | Description |
|
99 |
+
| -------- | ---------- | --------- | ----------- |
|
100 |
+
| [Nusantara-0.8b-Indo-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q2_K.gguf) | Q2_K | 0.374 GB | smallest, significant quality loss - not recommended for most purposes |
|
101 |
+
| [Nusantara-0.8b-Indo-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q3_K_S.gguf) | Q3_K_S | 0.422 GB | very small, high quality loss |
|
102 |
+
| [Nusantara-0.8b-Indo-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q3_K_M.gguf) | Q3_K_M | 0.449 GB | very small, high quality loss |
|
103 |
+
| [Nusantara-0.8b-Indo-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q3_K_L.gguf) | Q3_K_L | 0.473 GB | small, substantial quality loss |
|
104 |
+
| [Nusantara-0.8b-Indo-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q4_0.gguf) | Q4_0 | 0.511 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
105 |
+
| [Nusantara-0.8b-Indo-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q4_K_S.gguf) | Q4_K_S | 0.513 GB | small, greater quality loss |
|
106 |
+
| [Nusantara-0.8b-Indo-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q4_K_M.gguf) | Q4_K_M | 0.531 GB | medium, balanced quality - recommended |
|
107 |
+
| [Nusantara-0.8b-Indo-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q5_0.gguf) | Q5_0 | 0.595 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
108 |
+
| [Nusantara-0.8b-Indo-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q5_K_S.gguf) | Q5_K_S | 0.595 GB | large, low quality loss - recommended |
|
109 |
+
| [Nusantara-0.8b-Indo-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q5_K_M.gguf) | Q5_K_M | 0.605 GB | large, very low quality loss - recommended |
|
110 |
+
| [Nusantara-0.8b-Indo-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q6_K.gguf) | Q6_K | 0.684 GB | very large, extremely low quality loss |
|
111 |
+
| [Nusantara-0.8b-Indo-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/Nusantara-0.8b-Indo-Chat-GGUF/blob/main/Nusantara-0.8b-Indo-Chat-Q8_0.gguf) | Q8_0 | 0.883 GB | very large, extremely low quality loss - not recommended |
|
112 |
+
|
113 |
+
|
114 |
+
## Downloading instruction
|
115 |
+
|
116 |
+
### Command line
|
117 |
+
|
118 |
+
Firstly, install Huggingface Client
|
119 |
+
|
120 |
+
```shell
|
121 |
+
pip install -U "huggingface_hub[cli]"
|
122 |
+
```
|
123 |
+
|
124 |
+
Then, downoad the individual model file the a local directory
|
125 |
+
|
126 |
+
```shell
|
127 |
+
huggingface-cli download tensorblock/Nusantara-0.8b-Indo-Chat-GGUF --include "Nusantara-0.8b-Indo-Chat-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
128 |
+
```
|
129 |
+
|
130 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
131 |
+
|
132 |
+
```shell
|
133 |
+
huggingface-cli download tensorblock/Nusantara-0.8b-Indo-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
134 |
+
```
|