Hugging Face's logo

tensorblock
/
SummLlama3.2-3B-GGUF

Summarization
Transformers
GGUF
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
0184e65
·
verified ·
1 Parent(s): e45ba7a

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +84 -0
  3. SummLlama3.2-3B-Q2_K.gguf +3 -0
  4. SummLlama3.2-3B-Q3_K_L.gguf +3 -0
  5. SummLlama3.2-3B-Q3_K_M.gguf +3 -0
  6. SummLlama3.2-3B-Q3_K_S.gguf +3 -0
  7. SummLlama3.2-3B-Q4_0.gguf +3 -0
  8. SummLlama3.2-3B-Q4_K_M.gguf +3 -0
  9. SummLlama3.2-3B-Q4_K_S.gguf +3 -0
  10. SummLlama3.2-3B-Q5_0.gguf +3 -0
  11. SummLlama3.2-3B-Q5_K_M.gguf +3 -0
  12. SummLlama3.2-3B-Q5_K_S.gguf +3 -0
  13. SummLlama3.2-3B-Q6_K.gguf +3 -0
  14. SummLlama3.2-3B-Q8_0.gguf +3 -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
+ SummLlama3.2-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ SummLlama3.2-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ SummLlama3.2-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ SummLlama3.2-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ SummLlama3.2-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ SummLlama3.2-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ SummLlama3.2-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ SummLlama3.2-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ SummLlama3.2-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ SummLlama3.2-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ SummLlama3.2-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ SummLlama3.2-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: DISLab/SummLlama3.2-3B
4
+ pipeline_tag: summarization
5
+ tags:
6
+ - TensorBlock
7
+ - GGUF
8
+ ---
9
+
10
+ <div style="width: auto; margin-left: auto; margin-right: auto">
11
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
12
+ </div>
13
+ <div style="display: flex; justify-content: space-between; width: 100%;">
14
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
15
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
16
+ 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>
17
+ </p>
18
+ </div>
19
+ </div>
20
+
21
+ ## DISLab/SummLlama3.2-3B - GGUF
22
+
23
+ This repo contains GGUF format model files for [DISLab/SummLlama3.2-3B](https://huggingface.co/DISLab/SummLlama3.2-3B).
24
+
25
+ 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).
26
+
27
+ <div style="text-align: left; margin: 20px 0;">
28
+ <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;">
29
+ Run them on the TensorBlock client using your local machine ↗
30
+ </a>
31
+ </div>
32
+
33
+ ## Prompt template
34
+
35
+ ```
36
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
37
+
38
+ Cutting Knowledge Date: December 2023
39
+ Today Date: 20 Nov 2024
40
+
41
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
42
+
43
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
44
+ ```
45
+
46
+ ## Model file specification
47
+
48
+ | Filename | Quant type | File Size | Description |
49
+ | -------- | ---------- | --------- | ----------- |
50
+ | [SummLlama3.2-3B-Q2_K.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q2_K.gguf) | Q2_K | 1.364 GB | smallest, significant quality loss - not recommended for most purposes |
51
+ | [SummLlama3.2-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q3_K_S.gguf) | Q3_K_S | 1.543 GB | very small, high quality loss |
52
+ | [SummLlama3.2-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q3_K_M.gguf) | Q3_K_M | 1.687 GB | very small, high quality loss |
53
+ | [SummLlama3.2-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q3_K_L.gguf) | Q3_K_L | 1.815 GB | small, substantial quality loss |
54
+ | [SummLlama3.2-3B-Q4_0.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q4_0.gguf) | Q4_0 | 1.917 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
55
+ | [SummLlama3.2-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q4_K_S.gguf) | Q4_K_S | 1.928 GB | small, greater quality loss |
56
+ | [SummLlama3.2-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q4_K_M.gguf) | Q4_K_M | 2.019 GB | medium, balanced quality - recommended |
57
+ | [SummLlama3.2-3B-Q5_0.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q5_0.gguf) | Q5_0 | 2.270 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
58
+ | [SummLlama3.2-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q5_K_S.gguf) | Q5_K_S | 2.270 GB | large, low quality loss - recommended |
59
+ | [SummLlama3.2-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q5_K_M.gguf) | Q5_K_M | 2.322 GB | large, very low quality loss - recommended |
60
+ | [SummLlama3.2-3B-Q6_K.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q6_K.gguf) | Q6_K | 2.644 GB | very large, extremely low quality loss |
61
+ | [SummLlama3.2-3B-Q8_0.gguf](https://huggingface.co/tensorblock/SummLlama3.2-3B-GGUF/blob/main/SummLlama3.2-3B-Q8_0.gguf) | Q8_0 | 3.422 GB | very large, extremely low quality loss - not recommended |
62
+
63
+
64
+ ## Downloading instruction
65
+
66
+ ### Command line
67
+
68
+ Firstly, install Huggingface Client
69
+
70
+ ```shell
71
+ pip install -U "huggingface_hub[cli]"
72
+ ```
73
+
74
+ Then, downoad the individual model file the a local directory
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/SummLlama3.2-3B-GGUF --include "SummLlama3.2-3B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
78
+ ```
79
+
80
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
81
+
82
+ ```shell
83
+ huggingface-cli download tensorblock/SummLlama3.2-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
84
+ ```
SummLlama3.2-3B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500a9fb0506f4287b8beebfce3cfe0bed299a27440dbbb59289182309f4d7032
3
+ size 1363935552
SummLlama3.2-3B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:975b706891f13400feba1238cffe4f4ac999c9caebc246a20e43bce4457d85b1
3
+ size 1815347520
SummLlama3.2-3B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510a9f757f2891e0272c9575eb6f40e9356f5413636ee5944c9672bef2155324
3
+ size 1687159104
SummLlama3.2-3B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c00654c5e25941ad2b1848678b476edb9b7a5108414557924803ebc7e9b6ec1d
3
+ size 1542848832
SummLlama3.2-3B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fea86b3466bd2322c9aaf1402fa601fcad7c92f1c00567bd46854299d9c9a8f
3
+ size 1917190464
SummLlama3.2-3B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc475fa7daff94c3df64968b626e74481f65222b614cafc0215b6f9b170866a
3
+ size 2019377472
SummLlama3.2-3B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e0877d69a3a6341f98bc596859cc03bc09c6ad7375e07357853856848ded79
3
+ size 1928200512
SummLlama3.2-3B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac3addf4dd7f158ac78dd4084c645c248bc163e6be54aa4b6dbdcbfb7b58582
3
+ size 2269512000
SummLlama3.2-3B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7a68096a996877ebe0660d5e72898ab00bdae76ed4620c33d5b60e8448e165
3
+ size 2322153792
SummLlama3.2-3B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1d9cdeaaf11689f19a4f42b813dd4ef6405346234384c8b733d5cc90572665
3
+ size 2269512000
SummLlama3.2-3B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ad3dd757d11d19fa098139b18f55de435023615e03a4c0782e62bbeab5c957
3
+ size 2643853632
SummLlama3.2-3B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c41a0d0eb4cd250e57086da6140c0b45dc9d000ee6a9664872c6c629a7a5053a
3
+ size 3421899072