Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Configurable-Llama-3-8B-v0.3-Q2_K.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q3_K_L.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q3_K_M.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q3_K_S.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q4_0.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q4_K_M.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q4_K_S.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q5_0.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q5_K_M.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q5_K_S.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q6_K.gguf +3 -0
- Configurable-Llama-3-8B-v0.3-Q8_0.gguf +3 -0
- README.md +78 -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 |
+
Configurable-Llama-3-8B-v0.3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Configurable-Llama-3-8B-v0.3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Configurable-Llama-3-8B-v0.3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Configurable-Llama-3-8B-v0.3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Configurable-Llama-3-8B-v0.3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Configurable-Llama-3-8B-v0.3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Configurable-Llama-3-8B-v0.3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Configurable-Llama-3-8B-v0.3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Configurable-Llama-3-8B-v0.3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Configurable-Llama-3-8B-v0.3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Configurable-Llama-3-8B-v0.3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Configurable-Llama-3-8B-v0.3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Configurable-Llama-3-8B-v0.3-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:025a79ffac7ee10f1c6c4cf5c3a8871d5b47e9f4fc4482c5e82382f929763839
|
3 |
+
size 3179131616
|
Configurable-Llama-3-8B-v0.3-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79bf135f69e686fadf4d4246a2d2dccc078c38e194c6773e594345035ec92fda
|
3 |
+
size 4321956576
|
Configurable-Llama-3-8B-v0.3-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc60010e5f1eacfb08df466c2146f3327af21ff9c4ca4aa78f40ad0af45bdb8
|
3 |
+
size 4018918112
|
Configurable-Llama-3-8B-v0.3-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9bc245c14568dfd23331fd721448bcb26e5dae30885d438f32831511afb7f0a
|
3 |
+
size 3664499424
|
Configurable-Llama-3-8B-v0.3-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa99420afb157886c5b9c29e67ddad6a1e38f6f55309b58d508097bad2d068c
|
3 |
+
size 4661211872
|
Configurable-Llama-3-8B-v0.3-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bef07c5899839e058976d121ef9ca12c56d174a8ddfca99326fadc3d9446bf7b
|
3 |
+
size 4920734432
|
Configurable-Llama-3-8B-v0.3-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2df5cc7d680b4f2520608d5cf5a7b4b50833234c89105b5a6ec8e67425f9e12
|
3 |
+
size 4692669152
|
Configurable-Llama-3-8B-v0.3-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35759cdea1b205ee32b4e4a0326c2a421dde46a18202e492f29b9e3c3d690b9e
|
3 |
+
size 5599294176
|
Configurable-Llama-3-8B-v0.3-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d25fda612d585fff3b4d6f6f468caaaafa169a95ed8958806b091c1b438e4a0d
|
3 |
+
size 5732987616
|
Configurable-Llama-3-8B-v0.3-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bc94b20c08a4d239e9a6986ec2ed57f76d8f3d3ebdf6498aa5f22eccbc16cee
|
3 |
+
size 5599294176
|
Configurable-Llama-3-8B-v0.3-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b7508360436201cc52ccb0630d73abe172f201965ebd5a98b7fa468a06da539
|
3 |
+
size 6596006624
|
Configurable-Llama-3-8B-v0.3-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f663b63c37994c9e682e9d394faded045881101cba8e6d7dcffeae96b0257762
|
3 |
+
size 8540771040
|
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- safety
|
5 |
+
- TensorBlock
|
6 |
+
- GGUF
|
7 |
+
license: apache-2.0
|
8 |
+
datasets:
|
9 |
+
- vicgalle/configurable-system-prompt-multitask
|
10 |
+
base_model: vicgalle/Configurable-Llama-3-8B-v0.3
|
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 |
+
## vicgalle/Configurable-Llama-3-8B-v0.3 - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [vicgalle/Configurable-Llama-3-8B-v0.3](https://huggingface.co/vicgalle/Configurable-Llama-3-8B-v0.3).
|
27 |
+
|
28 |
+
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).
|
29 |
+
|
30 |
+
## Prompt template
|
31 |
+
|
32 |
+
```
|
33 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
34 |
+
|
35 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
36 |
+
|
37 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
38 |
+
```
|
39 |
+
|
40 |
+
## Model file specification
|
41 |
+
|
42 |
+
| Filename | Quant type | File Size | Description |
|
43 |
+
| -------- | ---------- | --------- | ----------- |
|
44 |
+
| [Configurable-Llama-3-8B-v0.3-Q2_K.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
45 |
+
| [Configurable-Llama-3-8B-v0.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
46 |
+
| [Configurable-Llama-3-8B-v0.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
47 |
+
| [Configurable-Llama-3-8B-v0.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
48 |
+
| [Configurable-Llama-3-8B-v0.3-Q4_0.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
49 |
+
| [Configurable-Llama-3-8B-v0.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
50 |
+
| [Configurable-Llama-3-8B-v0.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
51 |
+
| [Configurable-Llama-3-8B-v0.3-Q5_0.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
52 |
+
| [Configurable-Llama-3-8B-v0.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
53 |
+
| [Configurable-Llama-3-8B-v0.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
54 |
+
| [Configurable-Llama-3-8B-v0.3-Q6_K.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
55 |
+
| [Configurable-Llama-3-8B-v0.3-Q8_0.gguf](https://huggingface.co/tensorblock/Configurable-Llama-3-8B-v0.3-GGUF/tree/main/Configurable-Llama-3-8B-v0.3-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
56 |
+
|
57 |
+
|
58 |
+
## Downloading instruction
|
59 |
+
|
60 |
+
### Command line
|
61 |
+
|
62 |
+
Firstly, install Huggingface Client
|
63 |
+
|
64 |
+
```shell
|
65 |
+
pip install -U "huggingface_hub[cli]"
|
66 |
+
```
|
67 |
+
|
68 |
+
Then, downoad the individual model file the a local directory
|
69 |
+
|
70 |
+
```shell
|
71 |
+
huggingface-cli download tensorblock/Configurable-Llama-3-8B-v0.3-GGUF --include "Configurable-Llama-3-8B-v0.3-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
72 |
+
```
|
73 |
+
|
74 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
75 |
+
|
76 |
+
```shell
|
77 |
+
huggingface-cli download tensorblock/Configurable-Llama-3-8B-v0.3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
78 |
+
```
|