Hugging Face's logo

tensorblock
/
WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF

Text Generation
GGUF
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
72216c6
•
1 Parent(s): b55223e

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +77 -0
  3. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q2_K.gguf +3 -0
  4. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_L.gguf +3 -0
  5. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_M.gguf +3 -0
  6. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_S.gguf +3 -0
  7. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_0.gguf +3 -0
  8. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_M.gguf +3 -0
  9. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_S.gguf +3 -0
  10. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_0.gguf +3 -0
  11. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_M.gguf +3 -0
  12. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_S.gguf +3 -0
  13. WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q6_K.gguf +3 -0
  14. WebSquareAI-Instruct-llama-3-8B-v0.5.39-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
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: text-generation
5
+ license: cc-by-nc-4.0
6
+ base_model: kimwooglae/WebSquareAI-Instruct-llama-3-8B-v0.5.39
7
+ tags:
8
+ - TensorBlock
9
+ - GGUF
10
+ ---
11
+
12
+ <div style="width: auto; margin-left: auto; margin-right: auto">
13
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
14
+ </div>
15
+ <div style="display: flex; justify-content: space-between; width: 100%;">
16
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
17
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
18
+ 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>
19
+ </p>
20
+ </div>
21
+ </div>
22
+
23
+ ## kimwooglae/WebSquareAI-Instruct-llama-3-8B-v0.5.39 - GGUF
24
+
25
+ This repo contains GGUF format model files for [kimwooglae/WebSquareAI-Instruct-llama-3-8B-v0.5.39](https://huggingface.co/kimwooglae/WebSquareAI-Instruct-llama-3-8B-v0.5.39).
26
+
27
+ 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).
28
+
29
+ ## Prompt template
30
+
31
+ ```
32
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
33
+
34
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
35
+
36
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
37
+ ```
38
+
39
+ ## Model file specification
40
+
41
+ | Filename | Quant type | File Size | Description |
42
+ | -------- | ---------- | --------- | ----------- |
43
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q2_K.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
44
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_S.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
45
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_M.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
46
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_L.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
47
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_0.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
48
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_S.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
49
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_M.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
50
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_0.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
51
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_S.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
52
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_M.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
53
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q6_K.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
54
+ | [WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q8_0.gguf](https://huggingface.co/tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF/tree/main/WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
55
+
56
+
57
+ ## Downloading instruction
58
+
59
+ ### Command line
60
+
61
+ Firstly, install Huggingface Client
62
+
63
+ ```shell
64
+ pip install -U "huggingface_hub[cli]"
65
+ ```
66
+
67
+ Then, downoad the individual model file the a local directory
68
+
69
+ ```shell
70
+ huggingface-cli download tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF --include "WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q2_K.gguf" --local-dir MY_LOCAL_DIR
71
+ ```
72
+
73
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
74
+
75
+ ```shell
76
+ huggingface-cli download tensorblock/WebSquareAI-Instruct-llama-3-8B-v0.5.39-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
77
+ ```
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838b80c86bbaf806b9308dc871cb31e875dfb12c039897a74dc72521ba60956a
3
+ size 3179131616
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d2fa9b301ecd756a7ab501632a22973fb2251799fe6975035ebc0d38d40ed7
3
+ size 4321956576
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533a2df7981b48400a8cd3d29018f5d7c2599ef172e420fbd28725f5b172420a
3
+ size 4018918112
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2956148a04b8344cf76a89ee8dac1b984a6f86d4ab78e717730745a189440f
3
+ size 3664499424
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbfd5f51a7fff66e9f2240db26ed5fe8020ac85798ea6856175a377c7470234
3
+ size 4661211872
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33fa7125cf9649b1ccd2083b7221f0a57664c497679c9f339f207e7f897c178
3
+ size 4920734432
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9063872470b8b4e118b9a162e97ee14e9039d3776a459422884710f60b65577f
3
+ size 4692669152
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c66eac41c12fbd07c4384206b21acbcd69c95fbf009fa4b629db36acefb79f4
3
+ size 5599294176
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9285ddb998dc7ad78ef9416c42a7dc87c89fc88ebb5a891d1275d6b6fb78bdfa
3
+ size 5732987616
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08449e9d9387241aca884b9fb8994f17bf447cca872478ee2e83f1f116aa0fc
3
+ size 5599294176
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe32a8d54c3ee753e1de0bda3b8a897a89aa4db10f8f8f0d21613bf6038cf1d
3
+ size 6596006624
WebSquareAI-Instruct-llama-3-8B-v0.5.39-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56416cadee56f509d1edeb7e7c66233d878a00968ff5014d00edd3c02dc2a7ab
3
+ size 8540771040