Hugging Face's logo

tensorblock
/
SmolLM-1.7B-Instruct-GGUF

Transformers
GGUF
English
alignment-handbook
trl
unsloth
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
898d2d1
•
1 Parent(s): fbb561c

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +85 -0
  3. SmolLM-1.7B-Instruct-Q2_K.gguf +3 -0
  4. SmolLM-1.7B-Instruct-Q3_K_L.gguf +3 -0
  5. SmolLM-1.7B-Instruct-Q3_K_M.gguf +3 -0
  6. SmolLM-1.7B-Instruct-Q3_K_S.gguf +3 -0
  7. SmolLM-1.7B-Instruct-Q4_0.gguf +3 -0
  8. SmolLM-1.7B-Instruct-Q4_K_M.gguf +3 -0
  9. SmolLM-1.7B-Instruct-Q4_K_S.gguf +3 -0
  10. SmolLM-1.7B-Instruct-Q5_0.gguf +3 -0
  11. SmolLM-1.7B-Instruct-Q5_K_M.gguf +3 -0
  12. SmolLM-1.7B-Instruct-Q5_K_S.gguf +3 -0
  13. SmolLM-1.7B-Instruct-Q6_K.gguf +3 -0
  14. SmolLM-1.7B-Instruct-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
+ SmolLM-1.7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ SmolLM-1.7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ SmolLM-1.7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ SmolLM-1.7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ SmolLM-1.7B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ SmolLM-1.7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ SmolLM-1.7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ SmolLM-1.7B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ SmolLM-1.7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ SmolLM-1.7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ SmolLM-1.7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ SmolLM-1.7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: HuggingFaceTB/SmolLM-1.7B-Instruct
4
+ tags:
5
+ - alignment-handbook
6
+ - trl
7
+ - sft
8
+ - TensorBlock
9
+ - GGUF
10
+ datasets:
11
+ - Magpie-Align/Magpie-Pro-300K-Filtered
12
+ - bigcode/self-oss-instruct-sc2-exec-filter-50k
13
+ - teknium/OpenHermes-2.5
14
+ - HuggingFaceTB/everyday-conversations-llama3.1-2k
15
+ library_name: transformers
16
+ language:
17
+ - en
18
+ ---
19
+
20
+ <div style="width: auto; margin-left: auto; margin-right: auto">
21
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
+ </div>
23
+ <div style="display: flex; justify-content: space-between; width: 100%;">
24
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
25
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
26
+ 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>
27
+ </p>
28
+ </div>
29
+ </div>
30
+
31
+ ## HuggingFaceTB/SmolLM-1.7B-Instruct - GGUF
32
+
33
+ This repo contains GGUF format model files for [HuggingFaceTB/SmolLM-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct).
34
+
35
+ 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).
36
+
37
+ ## Prompt template
38
+
39
+ ```
40
+ <|im_start|>system
41
+ {system_prompt}<|im_end|>
42
+ <|im_start|>user
43
+ {prompt}<|im_end|>
44
+ <|im_start|>assistant
45
+ ```
46
+
47
+ ## Model file specification
48
+
49
+ | Filename | Quant type | File Size | Description |
50
+ | -------- | ---------- | --------- | ----------- |
51
+ | [SmolLM-1.7B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q2_K.gguf) | Q2_K | 0.628 GB | smallest, significant quality loss - not recommended for most purposes |
52
+ | [SmolLM-1.7B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 0.723 GB | very small, high quality loss |
53
+ | [SmolLM-1.7B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 0.801 GB | very small, high quality loss |
54
+ | [SmolLM-1.7B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 0.868 GB | small, substantial quality loss |
55
+ | [SmolLM-1.7B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q4_0.gguf) | Q4_0 | 0.923 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
56
+ | [SmolLM-1.7B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 0.931 GB | small, greater quality loss |
57
+ | [SmolLM-1.7B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 0.983 GB | medium, balanced quality - recommended |
58
+ | [SmolLM-1.7B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q5_0.gguf) | Q5_0 | 1.110 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
59
+ | [SmolLM-1.7B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 1.110 GB | large, low quality loss - recommended |
60
+ | [SmolLM-1.7B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 1.141 GB | large, very low quality loss - recommended |
61
+ | [SmolLM-1.7B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q6_K.gguf) | Q6_K | 1.309 GB | very large, extremely low quality loss |
62
+ | [SmolLM-1.7B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/SmolLM-1.7B-Instruct-GGUF/tree/main/SmolLM-1.7B-Instruct-Q8_0.gguf) | Q8_0 | 1.695 GB | very large, extremely low quality loss - not recommended |
63
+
64
+
65
+ ## Downloading instruction
66
+
67
+ ### Command line
68
+
69
+ Firstly, install Huggingface Client
70
+
71
+ ```shell
72
+ pip install -U "huggingface_hub[cli]"
73
+ ```
74
+
75
+ Then, downoad the individual model file the a local directory
76
+
77
+ ```shell
78
+ huggingface-cli download tensorblock/SmolLM-1.7B-Instruct-GGUF --include "SmolLM-1.7B-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
79
+ ```
80
+
81
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
82
+
83
+ ```shell
84
+ huggingface-cli download tensorblock/SmolLM-1.7B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
85
+ ```
SmolLM-1.7B-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edd9dcff86f47406e8a868ba1f8cbb5536cefb05b47c8361cb361a27c83c924
3
+ size 674583584
SmolLM-1.7B-Instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bbd1e2aa2fd11e43b129a831ff52a893f7d6bb09e25d324b0289b89d4c44bbb
3
+ size 932533280
SmolLM-1.7B-Instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77656e2d9f983a12b79be533fa8c58fab84bd5e6be21bf9e04a14ed51d55f11a
3
+ size 860181536
SmolLM-1.7B-Instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ccb67160b9d04524ec6601ffd776bd7ec2dad47dba07de290466c505f593ed
3
+ size 776819744
SmolLM-1.7B-Instruct-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c17f2fd5246eff751dfbcd551849fa2ccb66baa8f44e46a0e9ed728b59b21c
3
+ size 990729248
SmolLM-1.7B-Instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bc81769705d9e41beb09065dc7f5d126adb314b325e87c9ba93ef75cf16e53
3
+ size 1055609888
SmolLM-1.7B-Instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a697ee0c9005e6e6112cff8625d807b199b90071ef715e67334181949e2365
3
+ size 999117856
SmolLM-1.7B-Instruct-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b709c8143e3539f72288779c7c7f09ef970e79a199d427b69868226570e652
3
+ size 1192055840
SmolLM-1.7B-Instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2c7247e01a1640cb7a6f03f556510f2bfae9ca0a06342b5221b72017c9b3f8
3
+ size 1225479200
SmolLM-1.7B-Instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:101c6aa370634d72419dceb12f8f21b19910932556bc238ac84358e3c4c1cd3b
3
+ size 1192055840
SmolLM-1.7B-Instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc0369b47bdd0f8cbc6f18e76316a21f299c4d2e15d788406b5c65d5e1775ac4
3
+ size 1405965344
SmolLM-1.7B-Instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92ec99f014c96fb0413ed730c9154875f15678bb3767ebf6e403e76e6e1be3b
3
+ size 1820415008