Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +80 -0
- TinyLlama_v1.1-Q2_K.gguf +3 -0
- TinyLlama_v1.1-Q3_K_L.gguf +3 -0
- TinyLlama_v1.1-Q3_K_M.gguf +3 -0
- TinyLlama_v1.1-Q3_K_S.gguf +3 -0
- TinyLlama_v1.1-Q4_0.gguf +3 -0
- TinyLlama_v1.1-Q4_K_M.gguf +3 -0
- TinyLlama_v1.1-Q4_K_S.gguf +3 -0
- TinyLlama_v1.1-Q5_0.gguf +3 -0
- TinyLlama_v1.1-Q5_K_M.gguf +3 -0
- TinyLlama_v1.1-Q5_K_S.gguf +3 -0
- TinyLlama_v1.1-Q6_K.gguf +3 -0
- TinyLlama_v1.1-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 |
+
TinyLlama_v1.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
TinyLlama_v1.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
TinyLlama_v1.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
TinyLlama_v1.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
TinyLlama_v1.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
TinyLlama_v1.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
TinyLlama_v1.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
TinyLlama_v1.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
TinyLlama_v1.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
TinyLlama_v1.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
TinyLlama_v1.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
TinyLlama_v1.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- cerebras/SlimPajama-627B
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
base_model: TinyLlama/TinyLlama_v1.1
|
8 |
+
tags:
|
9 |
+
- TensorBlock
|
10 |
+
- GGUF
|
11 |
+
---
|
12 |
+
|
13 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
14 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
15 |
+
</div>
|
16 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
17 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
18 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
19 |
+
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>
|
20 |
+
</p>
|
21 |
+
</div>
|
22 |
+
</div>
|
23 |
+
|
24 |
+
## TinyLlama/TinyLlama_v1.1 - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1).
|
27 |
+
|
28 |
+
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).
|
29 |
+
|
30 |
+
<div style="text-align: left; margin: 20px 0;">
|
31 |
+
<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;">
|
32 |
+
Run them on the TensorBlock client using your local machine ↗
|
33 |
+
</a>
|
34 |
+
</div>
|
35 |
+
|
36 |
+
## Prompt template
|
37 |
+
|
38 |
+
```
|
39 |
+
|
40 |
+
```
|
41 |
+
|
42 |
+
## Model file specification
|
43 |
+
|
44 |
+
| Filename | Quant type | File Size | Description |
|
45 |
+
| -------- | ---------- | --------- | ----------- |
|
46 |
+
| [TinyLlama_v1.1-Q2_K.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q2_K.gguf) | Q2_K | 0.432 GB | smallest, significant quality loss - not recommended for most purposes |
|
47 |
+
| [TinyLlama_v1.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q3_K_S.gguf) | Q3_K_S | 0.499 GB | very small, high quality loss |
|
48 |
+
| [TinyLlama_v1.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q3_K_M.gguf) | Q3_K_M | 0.548 GB | very small, high quality loss |
|
49 |
+
| [TinyLlama_v1.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q3_K_L.gguf) | Q3_K_L | 0.592 GB | small, substantial quality loss |
|
50 |
+
| [TinyLlama_v1.1-Q4_0.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q4_0.gguf) | Q4_0 | 0.637 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
51 |
+
| [TinyLlama_v1.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q4_K_S.gguf) | Q4_K_S | 0.640 GB | small, greater quality loss |
|
52 |
+
| [TinyLlama_v1.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q4_K_M.gguf) | Q4_K_M | 0.668 GB | medium, balanced quality - recommended |
|
53 |
+
| [TinyLlama_v1.1-Q5_0.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q5_0.gguf) | Q5_0 | 0.766 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
54 |
+
| [TinyLlama_v1.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q5_K_S.gguf) | Q5_K_S | 0.766 GB | large, low quality loss - recommended |
|
55 |
+
| [TinyLlama_v1.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q5_K_M.gguf) | Q5_K_M | 0.782 GB | large, very low quality loss - recommended |
|
56 |
+
| [TinyLlama_v1.1-Q6_K.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q6_K.gguf) | Q6_K | 0.903 GB | very large, extremely low quality loss |
|
57 |
+
| [TinyLlama_v1.1-Q8_0.gguf](https://huggingface.co/tensorblock/TinyLlama_v1.1-GGUF/blob/main/TinyLlama_v1.1-Q8_0.gguf) | Q8_0 | 1.170 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/TinyLlama_v1.1-GGUF --include "TinyLlama_v1.1-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/TinyLlama_v1.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
80 |
+
```
|
TinyLlama_v1.1-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cdadd4b9720a9c43246452d5b7854be9b2ef840de0284f45b76ad94261361b9
|
3 |
+
size 432131072
|
TinyLlama_v1.1-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72db40b6f5c1c815e6c1eaa4bd52ee2a1dbb850c4192074a729dd13f677c4ca0
|
3 |
+
size 591526912
|
TinyLlama_v1.1-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a16967990eb4fa121a70bf58c677cccbe4901608684894897d7d0fa197f0477
|
3 |
+
size 548404224
|
TinyLlama_v1.1-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7421f180f18d6afcfd370e800ad3a47d72298a4090cd52ab9168f3eaf5ad1c64
|
3 |
+
size 499342336
|
TinyLlama_v1.1-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93b77d5a7aa426e84328c72df114d0b1f51a517486502472ffe783c8c79ba02c
|
3 |
+
size 636726272
|
TinyLlama_v1.1-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e6f38d8df36eeb87245e003171bc0f806fd87365bd4fe5937292f5deb575cd2
|
3 |
+
size 667814912
|
TinyLlama_v1.1-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbafdba608da313e3bfe08a6db7d3464adb29626ba643c95971da3634fbbc717
|
3 |
+
size 639872000
|
TinyLlama_v1.1-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:216fe7d7b1a69e9465c0eb614b53919951314eec23f835c4898dcce7b507bf8e
|
3 |
+
size 766028800
|
TinyLlama_v1.1-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd1c42c77abd765cbb39deca5b3e70607dbd5ea31378a16ed2b7e03b85ccd95a
|
3 |
+
size 782044160
|
TinyLlama_v1.1-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f51fe6e3ea0e00ef2dab54e412d65d23381491c79bcfd1f9aedef6aca8d18588
|
3 |
+
size 766028800
|
TinyLlama_v1.1-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6628abf277efa564eda069679c0acdbb8a5205a3aba4e6e7baf6ca3af87efcf9
|
3 |
+
size 903412736
|
TinyLlama_v1.1-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ecc21d355c71217c0710c6b86b260b4b462d8dd88981ef3f98994047f209568
|
3 |
+
size 1169808384
|