Hugging Face's logo

tensorblock
/
SmolLM-360M-GGUF

Transformers
GGUF
English
alignment-handbook
trl
unsloth
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
morriszms commited on
Commit
eb57105
•
1 Parent(s): e03e225

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. README.md +26 -22
  2. SmolLM-360M-Q2_K.gguf +2 -2
  3. SmolLM-360M-Q3_K_L.gguf +2 -2
  4. SmolLM-360M-Q3_K_M.gguf +2 -2
  5. SmolLM-360M-Q3_K_S.gguf +2 -2
  6. SmolLM-360M-Q4_0.gguf +2 -2
  7. SmolLM-360M-Q4_K_M.gguf +2 -2
  8. SmolLM-360M-Q4_K_S.gguf +2 -2
  9. SmolLM-360M-Q5_0.gguf +2 -2
  10. SmolLM-360M-Q5_K_M.gguf +2 -2
  11. SmolLM-360M-Q5_K_S.gguf +2 -2
  12. SmolLM-360M-Q6_K.gguf +2 -2
  13. SmolLM-360M-Q8_0.gguf +2 -2
README.md CHANGED
@@ -1,14 +1,20 @@
1
  ---
2
- library_name: transformers
3
  license: apache-2.0
4
- language:
5
- - en
6
- datasets:
7
- - HuggingFaceTB/smollm-corpus
8
- base_model: HuggingFaceTB/SmolLM-360M
9
  tags:
 
 
 
10
  - TensorBlock
11
  - GGUF
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  <div style="width: auto; margin-left: auto; margin-right: auto">
@@ -22,13 +28,12 @@ tags:
22
  </div>
23
  </div>
24
 
25
- ## HuggingFaceTB/SmolLM-360M - GGUF
26
 
27
- This repo contains GGUF format model files for [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M).
28
 
29
  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).
30
 
31
-
32
  <div style="text-align: left; margin: 20px 0;">
33
  <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;">
34
  Run them on the TensorBlock client using your local machine ↗
@@ -37,7 +42,6 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
37
 
38
  ## Prompt template
39
 
40
-
41
  ```
42
 
43
  ```
@@ -46,18 +50,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
46
 
47
  | Filename | Quant type | File Size | Description |
48
  | -------- | ---------- | --------- | ----------- |
49
- | [SmolLM-360M-Q2_K.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q2_K.gguf) | Q2_K | 0.204 GB | smallest, significant quality loss - not recommended for most purposes |
50
- | [SmolLM-360M-Q3_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q3_K_S.gguf) | Q3_K_S | 0.204 GB | very small, high quality loss |
51
- | [SmolLM-360M-Q3_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q3_K_M.gguf) | Q3_K_M | 0.219 GB | very small, high quality loss |
52
- | [SmolLM-360M-Q3_K_L.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q3_K_L.gguf) | Q3_K_L | 0.229 GB | small, substantial quality loss |
53
- | [SmolLM-360M-Q4_0.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q4_0.gguf) | Q4_0 | 0.213 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
54
- | [SmolLM-360M-Q4_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q4_K_S.gguf) | Q4_K_S | 0.242 GB | small, greater quality loss |
55
- | [SmolLM-360M-Q4_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q4_K_M.gguf) | Q4_K_M | 0.252 GB | medium, balanced quality - recommended |
56
- | [SmolLM-360M-Q5_0.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q5_0.gguf) | Q5_0 | 0.250 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
57
- | [SmolLM-360M-Q5_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q5_K_S.gguf) | Q5_K_S | 0.264 GB | large, low quality loss - recommended |
58
- | [SmolLM-360M-Q5_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q5_K_M.gguf) | Q5_K_M | 0.270 GB | large, very low quality loss - recommended |
59
- | [SmolLM-360M-Q6_K.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q6_K.gguf) | Q6_K | 0.342 GB | very large, extremely low quality loss |
60
- | [SmolLM-360M-Q8_0.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q8_0.gguf) | Q8_0 | 0.360 GB | very large, extremely low quality loss - not recommended |
61
 
62
 
63
  ## Downloading instruction
 
1
  ---
 
2
  license: apache-2.0
3
+ base_model: unsloth/SmolLM-360M
 
 
 
 
4
  tags:
5
+ - alignment-handbook
6
+ - trl
7
+ - unsloth
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">
 
28
  </div>
29
  </div>
30
 
31
+ ## unsloth/SmolLM-360M - GGUF
32
 
33
+ This repo contains GGUF format model files for [unsloth/SmolLM-360M](https://huggingface.co/unsloth/SmolLM-360M).
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
  <div style="text-align: left; margin: 20px 0;">
38
  <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;">
39
  Run them on the TensorBlock client using your local machine ↗
 
42
 
43
  ## Prompt template
44
 
 
45
  ```
46
 
47
  ```
 
50
 
51
  | Filename | Quant type | File Size | Description |
52
  | -------- | ---------- | --------- | ----------- |
53
+ | [SmolLM-360M-Q2_K.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q2_K.gguf) | Q2_K | 0.219 GB | smallest, significant quality loss - not recommended for most purposes |
54
+ | [SmolLM-360M-Q3_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q3_K_S.gguf) | Q3_K_S | 0.219 GB | very small, high quality loss |
55
+ | [SmolLM-360M-Q3_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q3_K_M.gguf) | Q3_K_M | 0.235 GB | very small, high quality loss |
56
+ | [SmolLM-360M-Q3_K_L.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q3_K_L.gguf) | Q3_K_L | 0.246 GB | small, substantial quality loss |
57
+ | [SmolLM-360M-Q4_0.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q4_0.gguf) | Q4_0 | 0.229 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
58
+ | [SmolLM-360M-Q4_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q4_K_S.gguf) | Q4_K_S | 0.260 GB | small, greater quality loss |
59
+ | [SmolLM-360M-Q4_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q4_K_M.gguf) | Q4_K_M | 0.271 GB | medium, balanced quality - recommended |
60
+ | [SmolLM-360M-Q5_0.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q5_0.gguf) | Q5_0 | 0.268 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
61
+ | [SmolLM-360M-Q5_K_S.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q5_K_S.gguf) | Q5_K_S | 0.283 GB | large, low quality loss - recommended |
62
+ | [SmolLM-360M-Q5_K_M.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q5_K_M.gguf) | Q5_K_M | 0.290 GB | large, very low quality loss - recommended |
63
+ | [SmolLM-360M-Q6_K.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q6_K.gguf) | Q6_K | 0.367 GB | very large, extremely low quality loss |
64
+ | [SmolLM-360M-Q8_0.gguf](https://huggingface.co/tensorblock/SmolLM-360M-GGUF/blob/main/SmolLM-360M-Q8_0.gguf) | Q8_0 | 0.386 GB | very large, extremely low quality loss - not recommended |
65
 
66
 
67
  ## Downloading instruction
SmolLM-360M-Q2_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b122171a910a1d47947bf979d6f39f12e607acc75eb0c0837a4755b2df9c6bd
3
- size 218673312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ce1cc8d2804d49070ba6ffa15cab18d0121598a848437b266e2965e277e84a6
3
+ size 218673888
SmolLM-360M-Q3_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:166f786cdb94e69bd49ba5f6e3bd514def474e8b95d5070054caefc55eaf388f
3
- size 246321312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3aa342b382426a9f5555045c23aa688c89fa7b744bdfff160dc5d2273384180
3
+ size 246321888
SmolLM-360M-Q3_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0af1e080080c318c6e3ca3a42302c449786212bc7155dd8170069c1ae472f9e3
3
- size 234686112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6065f9d75482c73bd30619042db1d799aa9005fb3575cd9a305cc054b06851f
3
+ size 234686688
SmolLM-360M-Q3_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d0162e91a25c6d4ce3228c7caa364a2fcb49d948f0e61217680023a472d935a
3
- size 218673312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350f3d8c60829d051e678faf21594e66d1803c82cc0cc955f6e3b88d89f66c79
3
+ size 218673888
SmolLM-360M-Q4_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42ec302aa3d088d7e32187643169968b94d2bf8c235d4d0e9a377c1e1c0237b0
3
- size 229118112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e02788d51152886048c581a110185272f9403e334667b7e03a0263e1d7f60e5
3
+ size 229118688
SmolLM-360M-Q4_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:556e3fb030cb0eefb1d8051e59a8030150185803c66ab69d17f97b38f487fd04
3
- size 270590112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa35354360a62bfaf4fcf439e570832ff7c1f077c52b8f44d64a25127a910b3e
3
+ size 270590688
SmolLM-360M-Q4_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ddc5d6a5197aeda6392868c946076cfaac3ed8f53ea68b11b2888cabb3ee0dc
3
- size 259914912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b516f1994ebce0ca3c71c7e9f08ab5424ab39c9690bde8dcaba71dafc6f9a39e
3
+ size 259915488
SmolLM-360M-Q5_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77a02cd86cfaa3c61c47ed723b84891e1a3e5e04382ce650c15bfc0b1c0f8556
3
- size 268439712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bac2e484a590a4acb796b7b7d50d950ce15d969e9b06ea94a50dc81f3ace9ef
3
+ size 268440288
SmolLM-360M-Q5_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:103595d13b6e0cf942ba0075b155d7d6669ae4ddcfca228227edd20711abc310
3
- size 289943712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3b5798b0190c6cb6612be7c9d8ba645d920e805378ce7bb11ee7a85d2980c7
3
+ size 289944288
SmolLM-360M-Q5_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e1ec306c4d9d609b7bc4cf23b0983d6c77c647972b3d81bb099764991947c1d
3
- size 283185312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f546e5985f46c1e9034ae448262e6de65ad99f7d58b6f7eb7da4931bf5ef964
3
+ size 283185888
SmolLM-360M-Q6_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aef98f1d3ba6dfb435bb214c56b03ed0f51572daf27d1b36223e4614f0ac1aa8
3
- size 367358112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b6452b3546a534b408fbe83fcabb587ebfb59e0dd296d41d24e3a38b857c42
3
+ size 367358688
SmolLM-360M-Q8_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34a8cc10b8283c3e943d06a99a90138b49640f30d934991562720f599c568f3e
3
- size 386404512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce6ac1ff6ed64067799a2b89e2114fbb0174208e29713d79f954447425a22a27
3
+ size 386405088