morriszms commited on
Commit
aa40553
·
verified ·
1 Parent(s): 491602a

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
+ granite-3.1-3b-a800m-base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ granite-3.1-3b-a800m-base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ granite-3.1-3b-a800m-base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ granite-3.1-3b-a800m-base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ granite-3.1-3b-a800m-base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ granite-3.1-3b-a800m-base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ granite-3.1-3b-a800m-base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ granite-3.1-3b-a800m-base-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ granite-3.1-3b-a800m-base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ granite-3.1-3b-a800m-base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ granite-3.1-3b-a800m-base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ granite-3.1-3b-a800m-base-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: text-generation
3
+ inference: false
4
+ license: apache-2.0
5
+ library_name: transformers
6
+ tags:
7
+ - language
8
+ - granite-3.1
9
+ - TensorBlock
10
+ - GGUF
11
+ base_model: ibm-granite/granite-3.1-3b-a800m-base
12
+ ---
13
+
14
+ <div style="width: auto; margin-left: auto; margin-right: auto">
15
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
16
+ </div>
17
+ <div style="display: flex; justify-content: space-between; width: 100%;">
18
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
19
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
20
+ 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>
21
+ </p>
22
+ </div>
23
+ </div>
24
+
25
+ ## ibm-granite/granite-3.1-3b-a800m-base - GGUF
26
+
27
+ This repo contains GGUF format model files for [ibm-granite/granite-3.1-3b-a800m-base](https://huggingface.co/ibm-granite/granite-3.1-3b-a800m-base).
28
+
29
+ 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).
30
+
31
+ <div style="text-align: left; margin: 20px 0;">
32
+ <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;">
33
+ Run them on the TensorBlock client using your local machine ↗
34
+ </a>
35
+ </div>
36
+
37
+ ## Prompt template
38
+
39
+ ```
40
+
41
+ ```
42
+
43
+ ## Model file specification
44
+
45
+ | Filename | Quant type | File Size | Description |
46
+ | -------- | ---------- | --------- | ----------- |
47
+ | [granite-3.1-3b-a800m-base-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q2_K.gguf) | Q2_K | 1.241 GB | smallest, significant quality loss - not recommended for most purposes |
48
+ | [granite-3.1-3b-a800m-base-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q3_K_S.gguf) | Q3_K_S | 1.456 GB | very small, high quality loss |
49
+ | [granite-3.1-3b-a800m-base-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q3_K_M.gguf) | Q3_K_M | 1.611 GB | very small, high quality loss |
50
+ | [granite-3.1-3b-a800m-base-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q3_K_L.gguf) | Q3_K_L | 1.742 GB | small, substantial quality loss |
51
+ | [granite-3.1-3b-a800m-base-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q4_0.gguf) | Q4_0 | 1.884 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
52
+ | [granite-3.1-3b-a800m-base-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q4_K_S.gguf) | Q4_K_S | 1.900 GB | small, greater quality loss |
53
+ | [granite-3.1-3b-a800m-base-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q4_K_M.gguf) | Q4_K_M | 2.017 GB | medium, balanced quality - recommended |
54
+ | [granite-3.1-3b-a800m-base-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q5_0.gguf) | Q5_0 | 2.287 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
55
+ | [granite-3.1-3b-a800m-base-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q5_K_S.gguf) | Q5_K_S | 2.287 GB | large, low quality loss - recommended |
56
+ | [granite-3.1-3b-a800m-base-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q5_K_M.gguf) | Q5_K_M | 2.355 GB | large, very low quality loss - recommended |
57
+ | [granite-3.1-3b-a800m-base-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q6_K.gguf) | Q6_K | 2.714 GB | very large, extremely low quality loss |
58
+ | [granite-3.1-3b-a800m-base-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.1-3b-a800m-base-GGUF/blob/main/granite-3.1-3b-a800m-base-Q8_0.gguf) | Q8_0 | 3.513 GB | very large, extremely low quality loss - not recommended |
59
+
60
+
61
+ ## Downloading instruction
62
+
63
+ ### Command line
64
+
65
+ Firstly, install Huggingface Client
66
+
67
+ ```shell
68
+ pip install -U "huggingface_hub[cli]"
69
+ ```
70
+
71
+ Then, downoad the individual model file the a local directory
72
+
73
+ ```shell
74
+ huggingface-cli download tensorblock/granite-3.1-3b-a800m-base-GGUF --include "granite-3.1-3b-a800m-base-Q2_K.gguf" --local-dir MY_LOCAL_DIR
75
+ ```
76
+
77
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
78
+
79
+ ```shell
80
+ huggingface-cli download tensorblock/granite-3.1-3b-a800m-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
81
+ ```
granite-3.1-3b-a800m-base-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64dd65123210355f2d159b716a7b33e79001e0476c61b8eed8d03666828e426e
3
+ size 1241360416
granite-3.1-3b-a800m-base-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53aa4bbedc74c7b12a8da7b669be2357ab3ecaafe6aa49c20cbcb87037f678bc
3
+ size 1741531168
granite-3.1-3b-a800m-base-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51aec25c15a692d92b03368e978554496dffa577c0b197cf7075dba3217bc660
3
+ size 1611180064
granite-3.1-3b-a800m-base-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d33842080e6272d04b53ad493562a01bfda9fac1a869a91781ed676ca021aa
3
+ size 1456056352
granite-3.1-3b-a800m-base-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e2977f02e99268b214de76d847d7ab69d17e55991e58148a5fc6e37ec41b73
3
+ size 1883875360
granite-3.1-3b-a800m-base-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ea92d8ef66f7cb05e7ba252cfa1a3ef5b3f3800e9ae81d43a45ae13d4ff92a
3
+ size 2016880672
granite-3.1-3b-a800m-base-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cab402378b2ef215006faac4d339b61aa4781b90aac20d8870598f39ef1c0d4
3
+ size 1899997216
granite-3.1-3b-a800m-base-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d4cc916782236a982077869ee45b5a46bd0327324787f0c3d409401141d125
3
+ size 2286528544
granite-3.1-3b-a800m-base-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1647e91d5809016f9dd4ce269af426e544fdae507ffa4b8788e8c4ddadfd80a9
3
+ size 2355046432
granite-3.1-3b-a800m-base-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c64493015adfea57542e3c930bc1ddbe3205dea42d130df80558a3a34df1e9
3
+ size 2286528544
granite-3.1-3b-a800m-base-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0731b7681fef171a0ac7c952988745875ca19c0fe4e8ca64014ca9cd620da21
3
+ size 2714347552
granite-3.1-3b-a800m-base-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8818d7b3bcb428109ddc794aeb67dbb354d0b7ccf8147c6269e33a2ff37d2641
3
+ size 3512772640