morriszms commited on
Commit
06ebb7c
1 Parent(s): af5a1b7

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
+ distilgpt2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ distilgpt2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ distilgpt2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ distilgpt2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ distilgpt2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ distilgpt2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ distilgpt2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ distilgpt2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ distilgpt2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ distilgpt2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ distilgpt2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ distilgpt2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - exbert
5
+ - TensorBlock
6
+ - GGUF
7
+ license: apache-2.0
8
+ datasets:
9
+ - openwebtext
10
+ co2_eq_emissions: 149200
11
+ base_model: distilbert/distilgpt2
12
+ model-index:
13
+ - name: distilgpt2
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: WikiText-103
20
+ type: wikitext
21
+ metrics:
22
+ - type: perplexity
23
+ value: 21.1
24
+ name: Perplexity
25
+ ---
26
+
27
+ <div style="width: auto; margin-left: auto; margin-right: auto">
28
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
29
+ </div>
30
+ <div style="display: flex; justify-content: space-between; width: 100%;">
31
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
32
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
33
+ 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>
34
+ </p>
35
+ </div>
36
+ </div>
37
+
38
+ ## distilbert/distilgpt2 - GGUF
39
+
40
+ This repo contains GGUF format model files for [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2).
41
+
42
+ 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).
43
+
44
+ ## Prompt template
45
+
46
+ ```
47
+
48
+ ```
49
+
50
+ ## Model file specification
51
+
52
+ | Filename | Quant type | File Size | Description |
53
+ | -------- | ---------- | --------- | ----------- |
54
+ | [distilgpt2-Q2_K.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q2_K.gguf) | Q2_K | 0.061 GB | smallest, significant quality loss - not recommended for most purposes |
55
+ | [distilgpt2-Q3_K_S.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q3_K_S.gguf) | Q3_K_S | 0.067 GB | very small, high quality loss |
56
+ | [distilgpt2-Q3_K_M.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q3_K_M.gguf) | Q3_K_M | 0.070 GB | very small, high quality loss |
57
+ | [distilgpt2-Q3_K_L.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q3_K_L.gguf) | Q3_K_L | 0.072 GB | small, substantial quality loss |
58
+ | [distilgpt2-Q4_0.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q4_0.gguf) | Q4_0 | 0.077 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
59
+ | [distilgpt2-Q4_K_S.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q4_K_S.gguf) | Q4_K_S | 0.077 GB | small, greater quality loss |
60
+ | [distilgpt2-Q4_K_M.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q4_K_M.gguf) | Q4_K_M | 0.079 GB | medium, balanced quality - recommended |
61
+ | [distilgpt2-Q5_0.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q5_0.gguf) | Q5_0 | 0.086 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
62
+ | [distilgpt2-Q5_K_S.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q5_K_S.gguf) | Q5_K_S | 0.086 GB | large, low quality loss - recommended |
63
+ | [distilgpt2-Q5_K_M.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q5_K_M.gguf) | Q5_K_M | 0.088 GB | large, very low quality loss - recommended |
64
+ | [distilgpt2-Q6_K.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q6_K.gguf) | Q6_K | 0.096 GB | very large, extremely low quality loss |
65
+ | [distilgpt2-Q8_0.gguf](https://huggingface.co/tensorblock/distilgpt2-GGUF/tree/main/distilgpt2-Q8_0.gguf) | Q8_0 | 0.123 GB | very large, extremely low quality loss - not recommended |
66
+
67
+
68
+ ## Downloading instruction
69
+
70
+ ### Command line
71
+
72
+ Firstly, install Huggingface Client
73
+
74
+ ```shell
75
+ pip install -U "huggingface_hub[cli]"
76
+ ```
77
+
78
+ Then, downoad the individual model file the a local directory
79
+
80
+ ```shell
81
+ huggingface-cli download tensorblock/distilgpt2-GGUF --include "distilgpt2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
82
+ ```
83
+
84
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
85
+
86
+ ```shell
87
+ huggingface-cli download tensorblock/distilgpt2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
88
+ ```
distilgpt2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700846bf963d4a188dd1ab3d7f19d0171297cc1e790c40d88a64f7e0631fe65c
3
+ size 65221280
distilgpt2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f72f5fd5e0e58833836ad14b539c0e3ec66935f24600e13fdb1e8aa120bd5e7
3
+ size 77629280
distilgpt2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14475df7d0afce621c049630a40b6fbe6eef8a05b009e8b0ec41ffedcc2f59e5
3
+ size 75417440
distilgpt2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d04e20f0295ed10672e6f326161abae1eaa22d52354b95b28933545ef85ec8
3
+ size 71657312
distilgpt2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e364012b3da695fd0bf7793bf589f9b1157e42730f04a9266fb381618ffff6e0
3
+ size 82423712
distilgpt2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482de941a6f0c3a4533faba6981fc15318e0212f70761d778cc0e3e63e42609f
3
+ size 84967328
distilgpt2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c8dc817a453df6b69b0c579f15021ec8caa93184082e75996d019fe0ba81dc
3
+ size 82423712
distilgpt2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2021615ab82f9a9b5fd805d784c06d1faa4d978c451bb30954699f4357986ba7
3
+ size 92556800
distilgpt2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:941cd80a64804d24a7bcbe83a0abb3d100576f4f5b2da6479719800e177236b9
3
+ size 94593536
distilgpt2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62e2721a4b3bd6b38b55e93f5039395c5ccb5e46a190827ed3435b867c19c2a
3
+ size 92556800
distilgpt2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd57742361bcc77e1f53e8752fc9970ccf6e0c39f51cb50b6066d26a2973ce6
3
+ size 103323200
distilgpt2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407f73e88c98d72fbdc8737a0de6947752b078bb8adb884674cadb40a361e06c
3
+ size 132303872