Hugging Face's logo

tensorblock
/
SmolLlamix-8x101M-take2-GGUF

GGUF
English
TensorBlock
GGUF
Model card Files Community
morriszms commited on
Commit
f902dee
·
verified ·
1 Parent(s): 7650d49

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +80 -0
  3. SmolLlamix-8x101M-take2-Q2_K.gguf +3 -0
  4. SmolLlamix-8x101M-take2-Q3_K_L.gguf +3 -0
  5. SmolLlamix-8x101M-take2-Q3_K_M.gguf +3 -0
  6. SmolLlamix-8x101M-take2-Q3_K_S.gguf +3 -0
  7. SmolLlamix-8x101M-take2-Q4_0.gguf +3 -0
  8. SmolLlamix-8x101M-take2-Q4_K_M.gguf +3 -0
  9. SmolLlamix-8x101M-take2-Q4_K_S.gguf +3 -0
  10. SmolLlamix-8x101M-take2-Q5_0.gguf +3 -0
  11. SmolLlamix-8x101M-take2-Q5_K_M.gguf +3 -0
  12. SmolLlamix-8x101M-take2-Q5_K_S.gguf +3 -0
  13. SmolLlamix-8x101M-take2-Q6_K.gguf +3 -0
  14. SmolLlamix-8x101M-take2-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
+ SmolLlamix-8x101M-take2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ SmolLlamix-8x101M-take2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ SmolLlamix-8x101M-take2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ SmolLlamix-8x101M-take2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ SmolLlamix-8x101M-take2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ SmolLlamix-8x101M-take2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ SmolLlamix-8x101M-take2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ SmolLlamix-8x101M-take2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ SmolLlamix-8x101M-take2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ SmolLlamix-8x101M-take2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ SmolLlamix-8x101M-take2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ SmolLlamix-8x101M-take2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - togethercomputer/RedPajama-Data-1T-Sample
5
+ language:
6
+ - en
7
+ base_model: chargoddard/SmolLlamix-8x101M-take2
8
+ tags:
9
+ - TensorBlock
10
+ - GGUF
11
+ ---
12
+
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <div style="display: flex; justify-content: space-between; width: 100%;">
17
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
19
+ 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>
20
+ </p>
21
+ </div>
22
+ </div>
23
+
24
+ ## chargoddard/SmolLlamix-8x101M-take2 - GGUF
25
+
26
+ This repo contains GGUF format model files for [chargoddard/SmolLlamix-8x101M-take2](https://huggingface.co/chargoddard/SmolLlamix-8x101M-take2).
27
+
28
+ 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).
29
+
30
+ <div style="text-align: left; margin: 20px 0;">
31
+ <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;">
32
+ Run them on the TensorBlock client using your local machine ↗
33
+ </a>
34
+ </div>
35
+
36
+ ## Prompt template
37
+
38
+ ```
39
+
40
+ ```
41
+
42
+ ## Model file specification
43
+
44
+ | Filename | Quant type | File Size | Description |
45
+ | -------- | ---------- | --------- | ----------- |
46
+ | [SmolLlamix-8x101M-take2-Q2_K.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q2_K.gguf) | Q2_K | 0.158 GB | smallest, significant quality loss - not recommended for most purposes |
47
+ | [SmolLlamix-8x101M-take2-Q3_K_S.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q3_K_S.gguf) | Q3_K_S | 0.184 GB | very small, high quality loss |
48
+ | [SmolLlamix-8x101M-take2-Q3_K_M.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q3_K_M.gguf) | Q3_K_M | 0.199 GB | very small, high quality loss |
49
+ | [SmolLlamix-8x101M-take2-Q3_K_L.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q3_K_L.gguf) | Q3_K_L | 0.212 GB | small, substantial quality loss |
50
+ | [SmolLlamix-8x101M-take2-Q4_0.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q4_0.gguf) | Q4_0 | 0.233 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
51
+ | [SmolLlamix-8x101M-take2-Q4_K_S.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q4_K_S.gguf) | Q4_K_S | 0.233 GB | small, greater quality loss |
52
+ | [SmolLlamix-8x101M-take2-Q4_K_M.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q4_K_M.gguf) | Q4_K_M | 0.243 GB | medium, balanced quality - recommended |
53
+ | [SmolLlamix-8x101M-take2-Q5_0.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q5_0.gguf) | Q5_0 | 0.279 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
54
+ | [SmolLlamix-8x101M-take2-Q5_K_S.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q5_K_S.gguf) | Q5_K_S | 0.279 GB | large, low quality loss - recommended |
55
+ | [SmolLlamix-8x101M-take2-Q5_K_M.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q5_K_M.gguf) | Q5_K_M | 0.284 GB | large, very low quality loss - recommended |
56
+ | [SmolLlamix-8x101M-take2-Q6_K.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q6_K.gguf) | Q6_K | 0.328 GB | very large, extremely low quality loss |
57
+ | [SmolLlamix-8x101M-take2-Q8_0.gguf](https://huggingface.co/tensorblock/SmolLlamix-8x101M-take2-GGUF/blob/main/SmolLlamix-8x101M-take2-Q8_0.gguf) | Q8_0 | 0.424 GB | very large, extremely low quality loss - not recommended |
58
+
59
+
60
+ ## Downloading instruction
61
+
62
+ ### Command line
63
+
64
+ Firstly, install Huggingface Client
65
+
66
+ ```shell
67
+ pip install -U "huggingface_hub[cli]"
68
+ ```
69
+
70
+ Then, downoad the individual model file the a local directory
71
+
72
+ ```shell
73
+ huggingface-cli download tensorblock/SmolLlamix-8x101M-take2-GGUF --include "SmolLlamix-8x101M-take2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
74
+ ```
75
+
76
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
77
+
78
+ ```shell
79
+ huggingface-cli download tensorblock/SmolLlamix-8x101M-take2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
80
+ ```
SmolLlamix-8x101M-take2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce60c25b0af1011e7b3c00f021854717a4015fdfbe5f953c54bbf292069f95ac
3
+ size 158335456
SmolLlamix-8x101M-take2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959bf314ceedc7161641d9f13a2897706cdd47657a810588c4e4fc6ceeaf4901
3
+ size 212487904
SmolLlamix-8x101M-take2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c11eb73046c9d550ce985ed160eff29223c8a85c3ff6d789217166dd7ae6a53
3
+ size 199244512
SmolLlamix-8x101M-take2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d6f7f481294aebee1ea98b8ebf9b40a1637c13f0c6bd5f3f66df68bb163820c
3
+ size 184204000
SmolLlamix-8x101M-take2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf504ad986b47fbb2b0c0faf327cffc2add72e42d5c98e67d838f064b245417
3
+ size 232630240
SmolLlamix-8x101M-take2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fffe2bd81b4256db750f79cc964d5f2a122852f66fe1d1e9a16b151d1ad372bc
3
+ size 242804704
SmolLlamix-8x101M-take2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63953c60677ca4b8ad829283ac30f28680f968a026820f4484f546a18439d052
3
+ size 233072608
SmolLlamix-8x101M-take2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e49accbabd2e789fd903c3d4d065e34ce3dea42f304ceec3a3cf80904e73fe0
3
+ size 279066592
SmolLlamix-8x101M-take2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ba8619b9660e3bb594cabc90fb8e5e59009bf4ab3e2b369cc4e307af5e5e70
3
+ size 284080096
SmolLlamix-8x101M-take2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca917b7150a5b2b15f66041d4045ee9e4d3a1613c8ad5f9e62639b88a04e0c0
3
+ size 279066592
SmolLlamix-8x101M-take2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9943dfe27684f53927e21a8453b5e3876993ff3d1c3e8a9c38e8344913fba5f
3
+ size 328405216
SmolLlamix-8x101M-take2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca62296bbc9909356d7dc6f2463a64c78e5cf58077abfcfe78ba862ea919d18f
3
+ size 424351456