Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- L3-8B-Stheno-v3.3-32K-Q2_K.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q3_K_L.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q3_K_M.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q3_K_S.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q4_0.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q4_K_M.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q4_K_S.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q5_0.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q5_K_M.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q5_K_S.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q6_K.gguf +3 -0
- L3-8B-Stheno-v3.3-32K-Q8_0.gguf +3 -0
- README.md +82 -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 |
+
L3-8B-Stheno-v3.3-32K-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
L3-8B-Stheno-v3.3-32K-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
L3-8B-Stheno-v3.3-32K-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
L3-8B-Stheno-v3.3-32K-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
L3-8B-Stheno-v3.3-32K-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
L3-8B-Stheno-v3.3-32K-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
L3-8B-Stheno-v3.3-32K-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
L3-8B-Stheno-v3.3-32K-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
L3-8B-Stheno-v3.3-32K-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
L3-8B-Stheno-v3.3-32K-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
L3-8B-Stheno-v3.3-32K-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
L3-8B-Stheno-v3.3-32K-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
L3-8B-Stheno-v3.3-32K-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71605863667c3a13b95e77a456cd693699707c821232de70ca3b3a9825846428
|
3 |
+
size 3179131648
|
L3-8B-Stheno-v3.3-32K-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb0705fba9eb7e0dd3befb4de7ae50f734a031a8440275a62f14c999be69814
|
3 |
+
size 4321956608
|
L3-8B-Stheno-v3.3-32K-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a46d416009520471783d383e4c33d5e1ee2471526bb27ea0e059133764362a5
|
3 |
+
size 4018918144
|
L3-8B-Stheno-v3.3-32K-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d24de8fbfc7efcb2a15144bfb81ffc2b95e994c5b0198ac4a930724c90725965
|
3 |
+
size 3664499456
|
L3-8B-Stheno-v3.3-32K-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20bf804cfdb0508d2041b50dba7d5d0b946ed943e65e300ba6b1b45d7d3f2929
|
3 |
+
size 4661211904
|
L3-8B-Stheno-v3.3-32K-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa1cff10baacd856d08457f2dcff7a74cff6c3bb055ed6cdd7b17521aab76638
|
3 |
+
size 4920734464
|
L3-8B-Stheno-v3.3-32K-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfcc44b5a5679b2ba88852a262b7b42b4dfd263bd02c7b4e83caf8398bc991b2
|
3 |
+
size 4692669184
|
L3-8B-Stheno-v3.3-32K-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ef70c95bf063a063ab9bb87ee5c5d4ba5a16eaa9912cf40f7dbbdde93a0c8f0
|
3 |
+
size 5599294208
|
L3-8B-Stheno-v3.3-32K-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:949f6bd7b66e605c286d3ab0a27839e9b5e3597aa37203b15b46bc583259189b
|
3 |
+
size 5732987648
|
L3-8B-Stheno-v3.3-32K-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a24567304f81e2c3b3f9d1211c4d739235ed0a0dd3a2ddeb9c9c291f15cf8a57
|
3 |
+
size 5599294208
|
L3-8B-Stheno-v3.3-32K-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68ac551d0222a1e2317d27e0859db42ea7ab5468ef6be18fe3fe3ba0d0949925
|
3 |
+
size 6596006656
|
L3-8B-Stheno-v3.3-32K-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae48e9fcea19ac026ec460df91d902dfaa1f80c0684336b923988b454481d96c
|
3 |
+
size 8540771072
|
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- TensorBlock
|
7 |
+
- GGUF
|
8 |
+
base_model: Sao10K/L3-8B-Stheno-v3.3-32K
|
9 |
+
---
|
10 |
+
|
11 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
12 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
13 |
+
</div>
|
14 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
15 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
16 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
17 |
+
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>
|
18 |
+
</p>
|
19 |
+
</div>
|
20 |
+
</div>
|
21 |
+
|
22 |
+
## Sao10K/L3-8B-Stheno-v3.3-32K - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [Sao10K/L3-8B-Stheno-v3.3-32K](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.3-32K).
|
25 |
+
|
26 |
+
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).
|
27 |
+
|
28 |
+
<div style="text-align: left; margin: 20px 0;">
|
29 |
+
<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;">
|
30 |
+
Run them on the TensorBlock client using your local machine ↗
|
31 |
+
</a>
|
32 |
+
</div>
|
33 |
+
|
34 |
+
## Prompt template
|
35 |
+
|
36 |
+
```
|
37 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
38 |
+
|
39 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
40 |
+
|
41 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
42 |
+
```
|
43 |
+
|
44 |
+
## Model file specification
|
45 |
+
|
46 |
+
| Filename | Quant type | File Size | Description |
|
47 |
+
| -------- | ---------- | --------- | ----------- |
|
48 |
+
| [L3-8B-Stheno-v3.3-32K-Q2_K.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
|
49 |
+
| [L3-8B-Stheno-v3.3-32K-Q3_K_S.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q3_K_S.gguf) | Q3_K_S | 3.664 GB | very small, high quality loss |
|
50 |
+
| [L3-8B-Stheno-v3.3-32K-Q3_K_M.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
|
51 |
+
| [L3-8B-Stheno-v3.3-32K-Q3_K_L.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
|
52 |
+
| [L3-8B-Stheno-v3.3-32K-Q4_0.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
53 |
+
| [L3-8B-Stheno-v3.3-32K-Q4_K_S.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
|
54 |
+
| [L3-8B-Stheno-v3.3-32K-Q4_K_M.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
|
55 |
+
| [L3-8B-Stheno-v3.3-32K-Q5_0.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
56 |
+
| [L3-8B-Stheno-v3.3-32K-Q5_K_S.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
|
57 |
+
| [L3-8B-Stheno-v3.3-32K-Q5_K_M.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
|
58 |
+
| [L3-8B-Stheno-v3.3-32K-Q6_K.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
|
59 |
+
| [L3-8B-Stheno-v3.3-32K-Q8_0.gguf](https://huggingface.co/tensorblock/L3-8B-Stheno-v3.3-32K-GGUF/blob/main/L3-8B-Stheno-v3.3-32K-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
|
60 |
+
|
61 |
+
|
62 |
+
## Downloading instruction
|
63 |
+
|
64 |
+
### Command line
|
65 |
+
|
66 |
+
Firstly, install Huggingface Client
|
67 |
+
|
68 |
+
```shell
|
69 |
+
pip install -U "huggingface_hub[cli]"
|
70 |
+
```
|
71 |
+
|
72 |
+
Then, downoad the individual model file the a local directory
|
73 |
+
|
74 |
+
```shell
|
75 |
+
huggingface-cli download tensorblock/L3-8B-Stheno-v3.3-32K-GGUF --include "L3-8B-Stheno-v3.3-32K-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
76 |
+
```
|
77 |
+
|
78 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
79 |
+
|
80 |
+
```shell
|
81 |
+
huggingface-cli download tensorblock/L3-8B-Stheno-v3.3-32K-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
82 |
+
```
|