Hugging Face's logo

tensorblock
/
OpenThaiLLM-Prebuilt-7B-GGUF

Text Generation
GGUF
Thai
Chinese
English
chemistry
biology
finance
legal
code
medical
text-generation-inference
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
25dde78
·
verified ·
1 Parent(s): 1b988f2

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. OpenThaiLLM-Prebuilt-7B-Q2_K.gguf +3 -0
  3. OpenThaiLLM-Prebuilt-7B-Q3_K_L.gguf +3 -0
  4. OpenThaiLLM-Prebuilt-7B-Q3_K_M.gguf +3 -0
  5. OpenThaiLLM-Prebuilt-7B-Q3_K_S.gguf +3 -0
  6. OpenThaiLLM-Prebuilt-7B-Q4_0.gguf +3 -0
  7. OpenThaiLLM-Prebuilt-7B-Q4_K_M.gguf +3 -0
  8. OpenThaiLLM-Prebuilt-7B-Q4_K_S.gguf +3 -0
  9. OpenThaiLLM-Prebuilt-7B-Q5_0.gguf +3 -0
  10. OpenThaiLLM-Prebuilt-7B-Q5_K_M.gguf +3 -0
  11. OpenThaiLLM-Prebuilt-7B-Q5_K_S.gguf +3 -0
  12. OpenThaiLLM-Prebuilt-7B-Q6_K.gguf +3 -0
  13. OpenThaiLLM-Prebuilt-7B-Q8_0.gguf +3 -0
  14. README.md +94 -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
+ OpenThaiLLM-Prebuilt-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ OpenThaiLLM-Prebuilt-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ OpenThaiLLM-Prebuilt-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ OpenThaiLLM-Prebuilt-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ OpenThaiLLM-Prebuilt-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ OpenThaiLLM-Prebuilt-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ OpenThaiLLM-Prebuilt-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ OpenThaiLLM-Prebuilt-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ OpenThaiLLM-Prebuilt-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ OpenThaiLLM-Prebuilt-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ OpenThaiLLM-Prebuilt-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ OpenThaiLLM-Prebuilt-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
OpenThaiLLM-Prebuilt-7B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d6283eb7fb96ca5bcfe787a65cb51466a252c2841e28f6009d6e92b97ee899
3
+ size 3015940384
OpenThaiLLM-Prebuilt-7B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba18af3dd398aa773996ab47f6f33d87bd5d85bbee456a6ca2a420be4a8e4bf
3
+ size 4088459552
OpenThaiLLM-Prebuilt-7B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229430d97d0ce598cc6820526408f16f6a1cda1c94184e157938ed2a78d7fa00
3
+ size 3808391456
OpenThaiLLM-Prebuilt-7B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd079dc387bea86c7808348b26c32cf5e66377617e5444144bf7f4c2b67bcc14
3
+ size 3492368672
OpenThaiLLM-Prebuilt-7B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da5c428c09febdd085c4919a5804aef91b61c22e9935e085539143721556f74
3
+ size 4431391008
OpenThaiLLM-Prebuilt-7B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a77294bb4d534f6412f25584646f3d455c1873bf95ac24cde98bdff56eea73
3
+ size 4683073824
OpenThaiLLM-Prebuilt-7B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151d76ecfb5f1b264965259a4e6bc1f02f6a9e29855264120eda30f9c89cc2bd
3
+ size 4457769248
OpenThaiLLM-Prebuilt-7B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0bf05572a32dc7b25b2f0204f3f88b378fd2a8bf7d46177dd586448d26bbf2
3
+ size 5315176736
OpenThaiLLM-Prebuilt-7B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74afbb44452790f5cc0c963d5188518b51af2aa03adce8146f18d85fe746ea95
3
+ size 5444831520
OpenThaiLLM-Prebuilt-7B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29faafde48d02204af182e90f5f79f9f1111ac7ed7169e450d5c5d279693b401
3
+ size 5315176736
OpenThaiLLM-Prebuilt-7B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e433b29ed675e2d50205d6896f0d72d28a371a82bd1537aea4710ff1b28808
3
+ size 6254199072
OpenThaiLLM-Prebuilt-7B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978cf51034ac4bbe65bc08f1443ab1f59bb2fd1857fea9aec3349c3f5c6ed9ea
3
+ size 8098525472
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - th
5
+ - zh
6
+ - en
7
+ metrics:
8
+ - accuracy
9
+ base_model: nectec/OpenThaiLLM-Prebuilt-7B
10
+ pipeline_tag: text-generation
11
+ tags:
12
+ - chemistry
13
+ - biology
14
+ - finance
15
+ - legal
16
+ - code
17
+ - medical
18
+ - text-generation-inference
19
+ - TensorBlock
20
+ - GGUF
21
+ ---
22
+
23
+ <div style="width: auto; margin-left: auto; margin-right: auto">
24
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
25
+ </div>
26
+ <div style="display: flex; justify-content: space-between; width: 100%;">
27
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
28
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
29
+ 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>
30
+ </p>
31
+ </div>
32
+ </div>
33
+
34
+ ## nectec/OpenThaiLLM-Prebuilt-7B - GGUF
35
+
36
+ This repo contains GGUF format model files for [nectec/OpenThaiLLM-Prebuilt-7B](https://huggingface.co/nectec/OpenThaiLLM-Prebuilt-7B).
37
+
38
+ 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).
39
+
40
+ <div style="text-align: left; margin: 20px 0;">
41
+ <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;">
42
+ Run them on the TensorBlock client using your local machine ↗
43
+ </a>
44
+ </div>
45
+
46
+ ## Prompt template
47
+
48
+ ```
49
+ <|im_start|>system
50
+ {system_prompt}<|im_end|>
51
+ <|im_start|>user
52
+ {prompt}<|im_end|>
53
+ <|im_start|>assistant
54
+ ```
55
+
56
+ ## Model file specification
57
+
58
+ | Filename | Quant type | File Size | Description |
59
+ | -------- | ---------- | --------- | ----------- |
60
+ | [OpenThaiLLM-Prebuilt-7B-Q2_K.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q2_K.gguf) | Q2_K | 3.016 GB | smallest, significant quality loss - not recommended for most purposes |
61
+ | [OpenThaiLLM-Prebuilt-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q3_K_S.gguf) | Q3_K_S | 3.492 GB | very small, high quality loss |
62
+ | [OpenThaiLLM-Prebuilt-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q3_K_M.gguf) | Q3_K_M | 3.808 GB | very small, high quality loss |
63
+ | [OpenThaiLLM-Prebuilt-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q3_K_L.gguf) | Q3_K_L | 4.088 GB | small, substantial quality loss |
64
+ | [OpenThaiLLM-Prebuilt-7B-Q4_0.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q4_0.gguf) | Q4_0 | 4.431 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
65
+ | [OpenThaiLLM-Prebuilt-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q4_K_S.gguf) | Q4_K_S | 4.458 GB | small, greater quality loss |
66
+ | [OpenThaiLLM-Prebuilt-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q4_K_M.gguf) | Q4_K_M | 4.683 GB | medium, balanced quality - recommended |
67
+ | [OpenThaiLLM-Prebuilt-7B-Q5_0.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q5_0.gguf) | Q5_0 | 5.315 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
68
+ | [OpenThaiLLM-Prebuilt-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q5_K_S.gguf) | Q5_K_S | 5.315 GB | large, low quality loss - recommended |
69
+ | [OpenThaiLLM-Prebuilt-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q5_K_M.gguf) | Q5_K_M | 5.445 GB | large, very low quality loss - recommended |
70
+ | [OpenThaiLLM-Prebuilt-7B-Q6_K.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q6_K.gguf) | Q6_K | 6.254 GB | very large, extremely low quality loss |
71
+ | [OpenThaiLLM-Prebuilt-7B-Q8_0.gguf](https://huggingface.co/tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF/blob/main/OpenThaiLLM-Prebuilt-7B-Q8_0.gguf) | Q8_0 | 8.099 GB | very large, extremely low quality loss - not recommended |
72
+
73
+
74
+ ## Downloading instruction
75
+
76
+ ### Command line
77
+
78
+ Firstly, install Huggingface Client
79
+
80
+ ```shell
81
+ pip install -U "huggingface_hub[cli]"
82
+ ```
83
+
84
+ Then, downoad the individual model file the a local directory
85
+
86
+ ```shell
87
+ huggingface-cli download tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF --include "OpenThaiLLM-Prebuilt-7B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
88
+ ```
89
+
90
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
91
+
92
+ ```shell
93
+ huggingface-cli download tensorblock/OpenThaiLLM-Prebuilt-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
94
+ ```