Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +80 -0
- prem-1B-SQL-Q2_K.gguf +3 -0
- prem-1B-SQL-Q3_K_L.gguf +3 -0
- prem-1B-SQL-Q3_K_M.gguf +3 -0
- prem-1B-SQL-Q3_K_S.gguf +3 -0
- prem-1B-SQL-Q4_0.gguf +3 -0
- prem-1B-SQL-Q4_K_M.gguf +3 -0
- prem-1B-SQL-Q4_K_S.gguf +3 -0
- prem-1B-SQL-Q5_0.gguf +3 -0
- prem-1B-SQL-Q5_K_M.gguf +3 -0
- prem-1B-SQL-Q5_K_S.gguf +3 -0
- prem-1B-SQL-Q6_K.gguf +3 -0
- prem-1B-SQL-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 |
+
prem-1B-SQL-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
prem-1B-SQL-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
prem-1B-SQL-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
prem-1B-SQL-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
prem-1B-SQL-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
prem-1B-SQL-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
prem-1B-SQL-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
prem-1B-SQL-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
prem-1B-SQL-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
prem-1B-SQL-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
prem-1B-SQL-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
prem-1B-SQL-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
datasets:
|
4 |
+
- premai-io/spider
|
5 |
+
- premai-io/domains
|
6 |
+
- premai-io/birdbench
|
7 |
+
- gretelai/synthetic_text_to_sql
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
base_model: premai-io/prem-1B-SQL
|
11 |
+
pipeline_tag: text2text-generation
|
12 |
+
tags:
|
13 |
+
- TensorBlock
|
14 |
+
- GGUF
|
15 |
+
---
|
16 |
+
|
17 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
18 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
19 |
+
</div>
|
20 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
21 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
22 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
23 |
+
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>
|
24 |
+
</p>
|
25 |
+
</div>
|
26 |
+
</div>
|
27 |
+
|
28 |
+
## premai-io/prem-1B-SQL - GGUF
|
29 |
+
|
30 |
+
This repo contains GGUF format model files for [premai-io/prem-1B-SQL](https://huggingface.co/premai-io/prem-1B-SQL).
|
31 |
+
|
32 |
+
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).
|
33 |
+
|
34 |
+
## Prompt template
|
35 |
+
|
36 |
+
```
|
37 |
+
<|begin▁of▁sentence|>{system_prompt}### Instruction:
|
38 |
+
{prompt}
|
39 |
+
### Response:
|
40 |
+
```
|
41 |
+
|
42 |
+
## Model file specification
|
43 |
+
|
44 |
+
| Filename | Quant type | File Size | Description |
|
45 |
+
| -------- | ---------- | --------- | ----------- |
|
46 |
+
| [prem-1B-SQL-Q2_K.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q2_K.gguf) | Q2_K | 0.521 GB | smallest, significant quality loss - not recommended for most purposes |
|
47 |
+
| [prem-1B-SQL-Q3_K_S.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q3_K_S.gguf) | Q3_K_S | 0.598 GB | very small, high quality loss |
|
48 |
+
| [prem-1B-SQL-Q3_K_M.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q3_K_M.gguf) | Q3_K_M | 0.656 GB | very small, high quality loss |
|
49 |
+
| [prem-1B-SQL-Q3_K_L.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q3_K_L.gguf) | Q3_K_L | 0.693 GB | small, substantial quality loss |
|
50 |
+
| [prem-1B-SQL-Q4_0.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q4_0.gguf) | Q4_0 | 0.723 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
51 |
+
| [prem-1B-SQL-Q4_K_S.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q4_K_S.gguf) | Q4_K_S | 0.758 GB | small, greater quality loss |
|
52 |
+
| [prem-1B-SQL-Q4_K_M.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q4_K_M.gguf) | Q4_K_M | 0.813 GB | medium, balanced quality - recommended |
|
53 |
+
| [prem-1B-SQL-Q5_0.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q5_0.gguf) | Q5_0 | 0.872 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
54 |
+
| [prem-1B-SQL-Q5_K_S.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q5_K_S.gguf) | Q5_K_S | 0.887 GB | large, low quality loss - recommended |
|
55 |
+
| [prem-1B-SQL-Q5_K_M.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q5_K_M.gguf) | Q5_K_M | 0.933 GB | large, very low quality loss - recommended |
|
56 |
+
| [prem-1B-SQL-Q6_K.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q6_K.gguf) | Q6_K | 1.091 GB | very large, extremely low quality loss |
|
57 |
+
| [prem-1B-SQL-Q8_0.gguf](https://huggingface.co/tensorblock/prem-1B-SQL-GGUF/tree/main/prem-1B-SQL-Q8_0.gguf) | Q8_0 | 1.334 GB | very large, extremely low quality loss - not recommended |
|
58 |
+
|
59 |
+
|
60 |
+
## Downloading instruction
|
61 |
+
|
62 |
+
### Command line
|
63 |
+
|
64 |
+
Firstly, install Huggingface Client
|
65 |
+
|
66 |
+
```shell
|
67 |
+
pip install -U "huggingface_hub[cli]"
|
68 |
+
```
|
69 |
+
|
70 |
+
Then, downoad the individual model file the a local directory
|
71 |
+
|
72 |
+
```shell
|
73 |
+
huggingface-cli download tensorblock/prem-1B-SQL-GGUF --include "prem-1B-SQL-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
74 |
+
```
|
75 |
+
|
76 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
77 |
+
|
78 |
+
```shell
|
79 |
+
huggingface-cli download tensorblock/prem-1B-SQL-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
80 |
+
```
|
prem-1B-SQL-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b1fc70dabfda692c7551b80edb2a4b355284f514d48e1e64e45ea159630c00e
|
3 |
+
size 559717952
|
prem-1B-SQL-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bbc1660bb10810a371fa7b34d177070cb181c886d01521dfe2a60553d0f5146
|
3 |
+
size 744455744
|
prem-1B-SQL-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b6221f68947654489f1e161bc350582fd9293e5d310fcd8be190f5678d374d2
|
3 |
+
size 704134720
|
prem-1B-SQL-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c3b5391e5720effa73e96f0f8f1b8b6eec025ad1cb6fb357d0439ead85ba6d1
|
3 |
+
size 641826368
|
prem-1B-SQL-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6dd070972e3f4c42c964ca440f1a9bd2e601cc91108014132069030019b07af
|
3 |
+
size 775937600
|
prem-1B-SQL-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:083e313c3d6da05d6c8811e37508b888105ff8bce1a10feb036a2302de45bddd
|
3 |
+
size 873455168
|
prem-1B-SQL-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d2a2679096657a07120a04972dbb503c27d31157b827359fe013dacfb0fa20d
|
3 |
+
size 813964864
|
prem-1B-SQL-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6968f9f1cda5585fa03d5a85245b5a93bb962a92a18a4135500e850d356e1e9c
|
3 |
+
size 935976512
|
prem-1B-SQL-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:276e9678a128dde872051170d1f35fe5399863a6de33bee9cedeab17b15688fd
|
3 |
+
size 1001840192
|
prem-1B-SQL-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5355b437328e87a3820291cf2c233e7c60ee57df32d960886f995e6918113d0
|
3 |
+
size 952884800
|
prem-1B-SQL-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce21929b879f69fa065350841a5d21ac04fbe51ed457716c6554ceb50944ab77
|
3 |
+
size 1171537472
|
prem-1B-SQL-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62226c3880891f6f560e1d3a259611e949d7d869cdc324fb1f35ab86a57f5076
|
3 |
+
size 1432092224
|