Hugging Face's logo

tensorblock
/
pythia-70m-deduped-GGUF

GGUF
PyTorch
English
causal-lm
pythia
TensorBlock
GGUF
Model card Files
xet
 Community
morriszms commited on
Commit
b3004cd
·
verified ·
1 Parent(s): ea1b56d

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +77 -0
  3. pythia-70m-deduped-Q2_K.gguf +3 -0
  4. pythia-70m-deduped-Q3_K_L.gguf +3 -0
  5. pythia-70m-deduped-Q3_K_M.gguf +3 -0
  6. pythia-70m-deduped-Q3_K_S.gguf +3 -0
  7. pythia-70m-deduped-Q4_0.gguf +3 -0
  8. pythia-70m-deduped-Q4_K_M.gguf +3 -0
  9. pythia-70m-deduped-Q4_K_S.gguf +3 -0
  10. pythia-70m-deduped-Q5_0.gguf +3 -0
  11. pythia-70m-deduped-Q5_K_M.gguf +3 -0
  12. pythia-70m-deduped-Q5_K_S.gguf +3 -0
  13. pythia-70m-deduped-Q6_K.gguf +3 -0
  14. pythia-70m-deduped-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
+ pythia-70m-deduped-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ pythia-70m-deduped-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ pythia-70m-deduped-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ pythia-70m-deduped-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ pythia-70m-deduped-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ pythia-70m-deduped-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ pythia-70m-deduped-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ pythia-70m-deduped-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ pythia-70m-deduped-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ pythia-70m-deduped-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ pythia-70m-deduped-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ pythia-70m-deduped-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - pytorch
6
+ - causal-lm
7
+ - pythia
8
+ - TensorBlock
9
+ - GGUF
10
+ license: apache-2.0
11
+ datasets:
12
+ - EleutherAI/the_pile_deduplicated
13
+ base_model: EleutherAI/pythia-70m-deduped
14
+ ---
15
+
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <div style="display: flex; justify-content: space-between; width: 100%;">
20
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
21
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
22
+ 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>
23
+ </p>
24
+ </div>
25
+ </div>
26
+
27
+ ## EleutherAI/pythia-70m-deduped - GGUF
28
+
29
+ This repo contains GGUF format model files for [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped).
30
+
31
+ 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).
32
+
33
+ ## Prompt template
34
+
35
+ ```
36
+
37
+ ```
38
+
39
+ ## Model file specification
40
+
41
+ | Filename | Quant type | File Size | Description |
42
+ | -------- | ---------- | --------- | ----------- |
43
+ | [pythia-70m-deduped-Q2_K.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q2_K.gguf) | Q2_K | 0.036 GB | smallest, significant quality loss - not recommended for most purposes |
44
+ | [pythia-70m-deduped-Q3_K_S.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q3_K_S.gguf) | Q3_K_S | 0.039 GB | very small, high quality loss |
45
+ | [pythia-70m-deduped-Q3_K_M.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q3_K_M.gguf) | Q3_K_M | 0.041 GB | very small, high quality loss |
46
+ | [pythia-70m-deduped-Q3_K_L.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q3_K_L.gguf) | Q3_K_L | 0.042 GB | small, substantial quality loss |
47
+ | [pythia-70m-deduped-Q4_0.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q4_0.gguf) | Q4_0 | 0.045 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
48
+ | [pythia-70m-deduped-Q4_K_S.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q4_K_S.gguf) | Q4_K_S | 0.045 GB | small, greater quality loss |
49
+ | [pythia-70m-deduped-Q4_K_M.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q4_K_M.gguf) | Q4_K_M | 0.046 GB | medium, balanced quality - recommended |
50
+ | [pythia-70m-deduped-Q5_0.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q5_0.gguf) | Q5_0 | 0.050 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
51
+ | [pythia-70m-deduped-Q5_K_S.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q5_K_S.gguf) | Q5_K_S | 0.050 GB | large, low quality loss - recommended |
52
+ | [pythia-70m-deduped-Q5_K_M.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q5_K_M.gguf) | Q5_K_M | 0.051 GB | large, very low quality loss - recommended |
53
+ | [pythia-70m-deduped-Q6_K.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q6_K.gguf) | Q6_K | 0.056 GB | very large, extremely low quality loss |
54
+ | [pythia-70m-deduped-Q8_0.gguf](https://huggingface.co/tensorblock/pythia-70m-deduped-GGUF/tree/main/pythia-70m-deduped-Q8_0.gguf) | Q8_0 | 0.071 GB | very large, extremely low quality loss - not recommended |
55
+
56
+
57
+ ## Downloading instruction
58
+
59
+ ### Command line
60
+
61
+ Firstly, install Huggingface Client
62
+
63
+ ```shell
64
+ pip install -U "huggingface_hub[cli]"
65
+ ```
66
+
67
+ Then, downoad the individual model file the a local directory
68
+
69
+ ```shell
70
+ huggingface-cli download tensorblock/pythia-70m-deduped-GGUF --include "pythia-70m-deduped-Q2_K.gguf" --local-dir MY_LOCAL_DIR
71
+ ```
72
+
73
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
74
+
75
+ ```shell
76
+ huggingface-cli download tensorblock/pythia-70m-deduped-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
77
+ ```
pythia-70m-deduped-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4d434bf8bbe1ed65bcd4703d95c682e056e18d945e7038189e5f14220d43ef
3
+ size 38507840
pythia-70m-deduped-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181e13f200c33c38e594df5fc923a25cf3c6ebc7e7567c6c983bc21c3426350f
3
+ size 44896064
pythia-70m-deduped-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e2141d76aee200a5be947f8740ae4ffc5bee7d2246b6bfbb1046613d6175be
3
+ size 43913024
pythia-70m-deduped-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a6ca0c67733865871b94c59c5dd7d4eaf7677c881423d11c4021de3b9a25d5
3
+ size 42241856
pythia-70m-deduped-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf877029f315e4b15cb2f1990a1450cd4280df7b4318afae84a20ac3ced9d2f
3
+ size 48169280
pythia-70m-deduped-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39a5c77425aea3bfc2782378be6b8b5a5c768494b5791b78dd239e3ecbf6de1
3
+ size 49299776
pythia-70m-deduped-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c686e4a5941919848e78c5128668662d7c91410c36031e682faf5ec80b5e8f5
3
+ size 48169280
pythia-70m-deduped-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191e96d727fb9376a4ac66de9fffa8c68821e85092520b95cb0436520e5775f4
3
+ size 53748032
pythia-70m-deduped-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9ca46671160452b91a8f3f9adf555536146ccf20526370b729330e1506cca9
3
+ size 54653248
pythia-70m-deduped-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48dc0657d68b471ca5f6174cd86e7e8a18b9fa1f65483a6489e0598aa7a23c6
3
+ size 53748032
pythia-70m-deduped-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2503c22f82cd603d30687bb9a8d25fd73b741b99de68b2430db1a37a7bf5e94e
3
+ size 59675456
pythia-70m-deduped-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd23e57db55c19e65576fb0ec484788ee45807553d412cbb6652a578d1522fe1
3
+ size 76721984