morriszms commited on
Commit
2a17ac2
1 Parent(s): 727502a

Upload folder using huggingface_hub

Browse files
.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
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f131e53be68ea2a51a3dfca9ba841e84ae34d0e3109174dfc81ca7ccfaa6b2b
3
+ size 4045598048
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8dd38e1dfe1d37877e5f41cd8a22c4368fc9bc0b1797d3d98ff71468eccefd
3
+ size 5696843104
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c868b781d19819f388f70cadf2b1b79baabe652fe1ec0d75cc882b7258c662f
3
+ size 5241761120
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0694fb323c3fa903565ea3741aa02d434d256267768d44b6371633324fca0c4c
3
+ size 4710657376
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427e19dd367498e4acb8aa426c937ec04fd4f889584162e5c2366ff35a0a14a2
3
+ size 6123351392
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e109d85e2fee8e2c9467149cbbaa377fa780844b69d4c7810ec0e3ab03d35a78
3
+ size 6512635232
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8776cbba34ace23e49f5a185c9fe4c461fc34da62eabdaaf297f28f1e9316ac6
3
+ size 6169488736
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2bc62192f0add095b9d06a83b10abacf976c1902587dfb6ae3bd60e2f5286f0
3
+ size 7452945760
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6833913c603967914d7d2ae7371cc2fc4d63ccadbc360230023c4490918343e
3
+ size 7653485920
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a626121735f02ef07afc48702ecc6cb4cef77dc0199d405da734f4852fc48030
3
+ size 7452945760
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae6902f87095c63f7d30a0ba6eb14b1945eb1d58a53bc76831321148cec8f25
3
+ size 8865639776
KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8afbfc1f53fd44343a212dd8b2433cef64854b8241def949bdd5c8d246306d63
3
+ size 11482361184
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p
4
+ tags:
5
+ - TensorBlock
6
+ - GGUF
7
+ ---
8
+
9
+ <div style="width: auto; margin-left: auto; margin-right: auto">
10
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
11
+ </div>
12
+ <div style="display: flex; justify-content: space-between; width: 100%;">
13
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
14
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
15
+ 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>
16
+ </p>
17
+ </div>
18
+ </div>
19
+
20
+ ## jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p - GGUF
21
+
22
+ This repo contains GGUF format model files for [jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p](https://huggingface.co/jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p).
23
+
24
+ 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).
25
+
26
+ ## Prompt template
27
+
28
+ ```
29
+
30
+ ```
31
+
32
+ ## Model file specification
33
+
34
+ | Filename | Quant type | File Size | Description |
35
+ | -------- | ---------- | --------- | ----------- |
36
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q2_K.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q2_K.gguf) | Q2_K | 3.768 GB | smallest, significant quality loss - not recommended for most purposes |
37
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_S.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_S.gguf) | Q3_K_S | 4.387 GB | very small, high quality loss |
38
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_M.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_M.gguf) | Q3_K_M | 4.882 GB | very small, high quality loss |
39
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_L.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q3_K_L.gguf) | Q3_K_L | 5.306 GB | small, substantial quality loss |
40
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_0.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_0.gguf) | Q4_0 | 5.703 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
41
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_S.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_S.gguf) | Q4_K_S | 5.746 GB | small, greater quality loss |
42
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_M.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q4_K_M.gguf) | Q4_K_M | 6.065 GB | medium, balanced quality - recommended |
43
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_0.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_0.gguf) | Q5_0 | 6.941 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
44
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_S.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_S.gguf) | Q5_K_S | 6.941 GB | large, low quality loss - recommended |
45
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_M.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q5_K_M.gguf) | Q5_K_M | 7.128 GB | large, very low quality loss - recommended |
46
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q6_K.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q6_K.gguf) | Q6_K | 8.257 GB | very large, extremely low quality loss |
47
+ | [KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q8_0.gguf](https://huggingface.co/tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF/tree/main/KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q8_0.gguf) | Q8_0 | 10.694 GB | very large, extremely low quality loss - not recommended |
48
+
49
+
50
+ ## Downloading instruction
51
+
52
+ ### Command line
53
+
54
+ Firstly, install Huggingface Client
55
+
56
+ ```shell
57
+ pip install -U "huggingface_hub[cli]"
58
+ ```
59
+
60
+ Then, downoad the individual model file the a local directory
61
+
62
+ ```shell
63
+ huggingface-cli download tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF --include "KoSoLAR-10.7B-v0.2_1.3_dedup_p-Q2_K.gguf" --local-dir MY_LOCAL_DIR
64
+ ```
65
+
66
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
67
+
68
+ ```shell
69
+ huggingface-cli download tensorblock/KoSoLAR-10.7B-v0.2_1.3_dedup_p-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
70
+ ```