Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +80 -0
- TinySwallow-1.5B-Instruct-ONNX-Q2_K.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q3_K_L.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q3_K_M.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q3_K_S.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q4_0.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q4_K_M.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q4_K_S.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q5_0.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q5_K_M.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q5_K_S.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-Q6_K.gguf +3 -0
- TinySwallow-1.5B-Instruct-ONNX-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 |
+
TinySwallow-1.5B-Instruct-ONNX-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
TinySwallow-1.5B-Instruct-ONNX-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
TinySwallow-1.5B-Instruct-ONNX-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
TinySwallow-1.5B-Instruct-ONNX-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
TinySwallow-1.5B-Instruct-ONNX-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
TinySwallow-1.5B-Instruct-ONNX-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
TinySwallow-1.5B-Instruct-ONNX-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
TinySwallow-1.5B-Instruct-ONNX-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
TinySwallow-1.5B-Instruct-ONNX-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
TinySwallow-1.5B-Instruct-ONNX-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
TinySwallow-1.5B-Instruct-ONNX-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
TinySwallow-1.5B-Instruct-ONNX-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers.js
|
| 3 |
+
base_model: onnx-community/TinySwallow-1.5B-Instruct-ONNX
|
| 4 |
+
tags:
|
| 5 |
+
- TensorBlock
|
| 6 |
+
- GGUF
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 10 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 11 |
+
</div>
|
| 12 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
| 13 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
| 14 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
| 15 |
+
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>
|
| 16 |
+
</p>
|
| 17 |
+
</div>
|
| 18 |
+
</div>
|
| 19 |
+
|
| 20 |
+
## onnx-community/TinySwallow-1.5B-Instruct-ONNX - GGUF
|
| 21 |
+
|
| 22 |
+
This repo contains GGUF format model files for [onnx-community/TinySwallow-1.5B-Instruct-ONNX](https://huggingface.co/onnx-community/TinySwallow-1.5B-Instruct-ONNX).
|
| 23 |
+
|
| 24 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
|
| 25 |
+
|
| 26 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 27 |
+
<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;">
|
| 28 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 29 |
+
</a>
|
| 30 |
+
</div>
|
| 31 |
+
|
| 32 |
+
## Prompt template
|
| 33 |
+
|
| 34 |
+
```
|
| 35 |
+
<|im_start|>system
|
| 36 |
+
{system_prompt}<|im_end|>
|
| 37 |
+
<|im_start|>user
|
| 38 |
+
{prompt}<|im_end|>
|
| 39 |
+
<|im_start|>assistant
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## Model file specification
|
| 43 |
+
|
| 44 |
+
| Filename | Quant type | File Size | Description |
|
| 45 |
+
| -------- | ---------- | --------- | ----------- |
|
| 46 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q2_K.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q2_K.gguf) | Q2_K | 0.006 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 47 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q3_K_S.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q3_K_S.gguf) | Q3_K_S | 0.006 GB | very small, high quality loss |
|
| 48 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q3_K_M.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q3_K_M.gguf) | Q3_K_M | 0.006 GB | very small, high quality loss |
|
| 49 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q3_K_L.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q3_K_L.gguf) | Q3_K_L | 0.006 GB | small, substantial quality loss |
|
| 50 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q4_0.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q4_0.gguf) | Q4_0 | 0.006 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 51 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q4_K_S.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q4_K_S.gguf) | Q4_K_S | 0.006 GB | small, greater quality loss |
|
| 52 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q4_K_M.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q4_K_M.gguf) | Q4_K_M | 0.006 GB | medium, balanced quality - recommended |
|
| 53 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q5_0.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q5_0.gguf) | Q5_0 | 0.006 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 54 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q5_K_S.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q5_K_S.gguf) | Q5_K_S | 0.006 GB | large, low quality loss - recommended |
|
| 55 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q5_K_M.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q5_K_M.gguf) | Q5_K_M | 0.006 GB | large, very low quality loss - recommended |
|
| 56 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q6_K.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q6_K.gguf) | Q6_K | 0.006 GB | very large, extremely low quality loss |
|
| 57 |
+
| [TinySwallow-1.5B-Instruct-ONNX-Q8_0.gguf](https://huggingface.co/tensorblock/TinySwallow-1.5B-Instruct-ONNX-GGUF/blob/main/TinySwallow-1.5B-Instruct-ONNX-Q8_0.gguf) | Q8_0 | 0.006 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/TinySwallow-1.5B-Instruct-ONNX-GGUF --include "TinySwallow-1.5B-Instruct-ONNX-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/TinySwallow-1.5B-Instruct-ONNX-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
| 80 |
+
```
|
TinySwallow-1.5B-Instruct-ONNX-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8ff501756ca5b4470980dfb7541a9d73ace2eb0b962f1b5107432e277e701d2
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ede5e8233ee4f3fe1e327b183b6e3fbd8a9a193a813a0ba32fb7987ff055925
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78b38b6e19acaf108c02fe80f16a0e77b3c04509207a50102247f8768cef6d86
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0db546e4c1aebfd266dd7da26c9d46bb5d61124af5f414ced7c34e0eab76a7e7
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:173f0a3a74753f97e76117206bf58fd3c5020683b4a4d545d46db84cb45e89fb
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:948bd21aac84f2cd7eea5595da9346a3100df9387adae6ba672323c56dd2b578
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a05f0d5fe54542ce4ffb51c14cfe632a52fcb29f5a58fde0b9e74c49270915ab
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfcb1fd04d177c40508aefda6c371af477a42aa2ba453341c1a2168ef1a03ee2
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f0137d8a86ec9daa6d31871f65a88062362ea5e04acd43df036e05bfce6d296
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e792eb92e2c8ef77b26df0525582a529bfb055151b2f0cdb6d1db05c595c7fd
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de737fb31821f1b621d87d6543d585e21a84755d822c3245097600de4a822293
|
| 3 |
+
size 5931648
|
TinySwallow-1.5B-Instruct-ONNX-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70818319c8f1bd2ac230ae9644f75caa8866603a63c33e450e42b69cc01fde43
|
| 3 |
+
size 5931648
|