Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +120 -0
- bloom-1b7-Q2_K.gguf +3 -0
- bloom-1b7-Q3_K_L.gguf +3 -0
- bloom-1b7-Q3_K_M.gguf +3 -0
- bloom-1b7-Q3_K_S.gguf +3 -0
- bloom-1b7-Q4_0.gguf +3 -0
- bloom-1b7-Q4_K_M.gguf +3 -0
- bloom-1b7-Q4_K_S.gguf +3 -0
- bloom-1b7-Q5_0.gguf +3 -0
- bloom-1b7-Q5_K_M.gguf +3 -0
- bloom-1b7-Q5_K_S.gguf +3 -0
- bloom-1b7-Q6_K.gguf +3 -0
- bloom-1b7-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 |
+
bloom-1b7-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
bloom-1b7-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
bloom-1b7-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
bloom-1b7-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
bloom-1b7-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
bloom-1b7-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
bloom-1b7-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
bloom-1b7-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
bloom-1b7-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
bloom-1b7-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
bloom-1b7-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
bloom-1b7-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: bigscience-bloom-rail-1.0
|
3 |
+
language:
|
4 |
+
- ak
|
5 |
+
- ar
|
6 |
+
- as
|
7 |
+
- bm
|
8 |
+
- bn
|
9 |
+
- ca
|
10 |
+
- code
|
11 |
+
- en
|
12 |
+
- es
|
13 |
+
- eu
|
14 |
+
- fon
|
15 |
+
- fr
|
16 |
+
- gu
|
17 |
+
- hi
|
18 |
+
- id
|
19 |
+
- ig
|
20 |
+
- ki
|
21 |
+
- kn
|
22 |
+
- lg
|
23 |
+
- ln
|
24 |
+
- ml
|
25 |
+
- mr
|
26 |
+
- ne
|
27 |
+
- nso
|
28 |
+
- ny
|
29 |
+
- or
|
30 |
+
- pa
|
31 |
+
- pt
|
32 |
+
- rn
|
33 |
+
- rw
|
34 |
+
- sn
|
35 |
+
- st
|
36 |
+
- sw
|
37 |
+
- ta
|
38 |
+
- te
|
39 |
+
- tn
|
40 |
+
- ts
|
41 |
+
- tum
|
42 |
+
- tw
|
43 |
+
- ur
|
44 |
+
- vi
|
45 |
+
- wo
|
46 |
+
- xh
|
47 |
+
- yo
|
48 |
+
- zh
|
49 |
+
- zhs
|
50 |
+
- zht
|
51 |
+
- zu
|
52 |
+
pipeline_tag: text-generation
|
53 |
+
base_model: bigscience/bloom-1b7
|
54 |
+
tags:
|
55 |
+
- TensorBlock
|
56 |
+
- GGUF
|
57 |
+
---
|
58 |
+
|
59 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
60 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
61 |
+
</div>
|
62 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
63 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
64 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
65 |
+
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>
|
66 |
+
</p>
|
67 |
+
</div>
|
68 |
+
</div>
|
69 |
+
|
70 |
+
## bigscience/bloom-1b7 - GGUF
|
71 |
+
|
72 |
+
This repo contains GGUF format model files for [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7).
|
73 |
+
|
74 |
+
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).
|
75 |
+
|
76 |
+
## Prompt template
|
77 |
+
|
78 |
+
```
|
79 |
+
|
80 |
+
```
|
81 |
+
|
82 |
+
## Model file specification
|
83 |
+
|
84 |
+
| Filename | Quant type | File Size | Description |
|
85 |
+
| -------- | ---------- | --------- | ----------- |
|
86 |
+
| [bloom-1b7-Q2_K.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q2_K.gguf) | Q2_K | 0.980 GB | smallest, significant quality loss - not recommended for most purposes |
|
87 |
+
| [bloom-1b7-Q3_K_S.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q3_K_S.gguf) | Q3_K_S | 1.096 GB | very small, high quality loss |
|
88 |
+
| [bloom-1b7-Q3_K_M.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q3_K_M.gguf) | Q3_K_M | 1.197 GB | very small, high quality loss |
|
89 |
+
| [bloom-1b7-Q3_K_L.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q3_K_L.gguf) | Q3_K_L | 1.254 GB | small, substantial quality loss |
|
90 |
+
| [bloom-1b7-Q4_0.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q4_0.gguf) | Q4_0 | 1.309 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
91 |
+
| [bloom-1b7-Q4_K_S.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q4_K_S.gguf) | Q4_K_S | 1.315 GB | small, greater quality loss |
|
92 |
+
| [bloom-1b7-Q4_K_M.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q4_K_M.gguf) | Q4_K_M | 1.392 GB | medium, balanced quality - recommended |
|
93 |
+
| [bloom-1b7-Q5_0.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q5_0.gguf) | Q5_0 | 1.509 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
94 |
+
| [bloom-1b7-Q5_K_S.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q5_K_S.gguf) | Q5_K_S | 1.509 GB | large, low quality loss - recommended |
|
95 |
+
| [bloom-1b7-Q5_K_M.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q5_K_M.gguf) | Q5_K_M | 1.571 GB | large, very low quality loss - recommended |
|
96 |
+
| [bloom-1b7-Q6_K.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q6_K.gguf) | Q6_K | 1.722 GB | very large, extremely low quality loss |
|
97 |
+
| [bloom-1b7-Q8_0.gguf](https://huggingface.co/tensorblock/bloom-1b7-GGUF/tree/main/bloom-1b7-Q8_0.gguf) | Q8_0 | 2.226 GB | very large, extremely low quality loss - not recommended |
|
98 |
+
|
99 |
+
|
100 |
+
## Downloading instruction
|
101 |
+
|
102 |
+
### Command line
|
103 |
+
|
104 |
+
Firstly, install Huggingface Client
|
105 |
+
|
106 |
+
```shell
|
107 |
+
pip install -U "huggingface_hub[cli]"
|
108 |
+
```
|
109 |
+
|
110 |
+
Then, downoad the individual model file the a local directory
|
111 |
+
|
112 |
+
```shell
|
113 |
+
huggingface-cli download tensorblock/bloom-1b7-GGUF --include "bloom-1b7-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
114 |
+
```
|
115 |
+
|
116 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
117 |
+
|
118 |
+
```shell
|
119 |
+
huggingface-cli download tensorblock/bloom-1b7-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
120 |
+
```
|
bloom-1b7-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33513bf30707c6ca0100431f4450ea39123fa6a8142bba81f9b62f4462ca92ec
|
3 |
+
size 1052760992
|
bloom-1b7-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f23c55c92d75864b81e526dde51b1040515b15fb21814f64fb8150c7a4ffda
|
3 |
+
size 1346378656
|
bloom-1b7-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e563af4f451b5434014bd5066327a55afb547a55f9f11d5ed74992509cab44
|
3 |
+
size 1285561248
|
bloom-1b7-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdfc6a5326e3f72c2dffc8b98377dc51180b90c2064f2fd148f8320ed2f79aa7
|
3 |
+
size 1176509344
|
bloom-1b7-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39565b47bd42407eb4d9182d7cf4d1d6d7e0e5e8964327a591b0fde13d26c64d
|
3 |
+
size 1405180832
|
bloom-1b7-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:761179cee22c3072a1c43f086b4ebfef81f5bec5071e7aabc4bc0b5c8635635f
|
3 |
+
size 1494834080
|
bloom-1b7-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9fce5e30a5538f04faf7485c2fbac005e6d1a773ff6c78083e0a1ed496b3867
|
3 |
+
size 1411472288
|
bloom-1b7-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dcb6e96f47e5e5aa092e57c8bd0102d80d16b08aa0927f242bf1f5b954d67e6
|
3 |
+
size 1620401056
|
bloom-1b7-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:184e2ba86b701a14ec7bbf027d7dc84cdba58994a86796ca95bed4f37e546c89
|
3 |
+
size 1687247776
|
bloom-1b7-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eab2d21f9c88b02f055f7d0d08a9c10cbaf6d2719cc6bf2ca532f016d6f12fa9
|
3 |
+
size 1620401056
|
bloom-1b7-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268376dfc80487d607cd4298afe8c07ef3e8d31a9dcc88e3660963d288a86f64
|
3 |
+
size 1849072544
|
bloom-1b7-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29660537b54aedf9cb486a0e138f8e86d07e9bdf7738df67ce265a89f09f3881
|
3 |
+
size 2390498208
|