Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Llama-3-8B-Instruct-RR-Q2_K.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q3_K_L.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q3_K_M.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q3_K_S.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q4_0.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q4_K_M.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q4_K_S.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q5_0.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q5_K_M.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q5_K_S.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q6_K.gguf +3 -0
- Llama-3-8B-Instruct-RR-Q8_0.gguf +3 -0
- README.md +79 -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 |
+
Llama-3-8B-Instruct-RR-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-3-8B-Instruct-RR-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-3-8B-Instruct-RR-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-3-8B-Instruct-RR-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-3-8B-Instruct-RR-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-3-8B-Instruct-RR-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-3-8B-Instruct-RR-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-3-8B-Instruct-RR-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-3-8B-Instruct-RR-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-3-8B-Instruct-RR-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-3-8B-Instruct-RR-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-3-8B-Instruct-RR-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-3-8B-Instruct-RR-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29c482cefa4225a7a974c08560def381a865a677ea27a891bb2c4ca83983e7fe
|
3 |
+
size 3179131392
|
Llama-3-8B-Instruct-RR-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75c8cfbfa361dc82dfd58d97641c3d41710fecd6fce839929a811fe35e8b4804
|
3 |
+
size 4321956352
|
Llama-3-8B-Instruct-RR-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:521706f8e1d4d9f80fab6c4f99b66bf51ec1d443d641b0cbe28ee5fbf2efe0c9
|
3 |
+
size 4018917888
|
Llama-3-8B-Instruct-RR-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50a8f1f1ff68166abc77cbf597ad3fe3de5605f9804792319fa4cdd12b602b01
|
3 |
+
size 3664499200
|
Llama-3-8B-Instruct-RR-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba7117501c7cebdbfb6980bca389b7a236cf89e9c1ece06d545d6380bc62727
|
3 |
+
size 4661211648
|
Llama-3-8B-Instruct-RR-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5889c5ade35273a2b84795da609d7b816cf511fcb31080e350a1df9625c99844
|
3 |
+
size 4920734208
|
Llama-3-8B-Instruct-RR-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fadc66fbf5769b35e55aa04d348d2ec062b5d2ac42fe847d3eba53beae681cdb
|
3 |
+
size 4692668928
|
Llama-3-8B-Instruct-RR-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b7cb5de2b82a02ba46ea76bd46b4be8498036d13842d435ac5defca0ca092e7
|
3 |
+
size 5599293952
|
Llama-3-8B-Instruct-RR-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ea7724a57c88e92dd7a812122721848fc7b3406198255f4259821d04fe857b1
|
3 |
+
size 5732987392
|
Llama-3-8B-Instruct-RR-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:890d0a9ce7c44a54c108fec62f367edcf19d993f372347d86af75298fc8e5c96
|
3 |
+
size 5599293952
|
Llama-3-8B-Instruct-RR-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cec67b3d48f1a2acb61a45d0dc452fce538273765e61a5de6fec3a13d0eff39
|
3 |
+
size 6596006400
|
Llama-3-8B-Instruct-RR-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc82bf9fab7ea10291d5ab8aa8fc7f4ff2737621d5d2ed5f780018994dd9dde9
|
3 |
+
size 8540770816
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: GraySwanAI/Llama-3-8B-Instruct-RR
|
3 |
+
tags:
|
4 |
+
- TensorBlock
|
5 |
+
- GGUF
|
6 |
+
---
|
7 |
+
|
8 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
9 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
10 |
+
</div>
|
11 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
12 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
13 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
14 |
+
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>
|
15 |
+
</p>
|
16 |
+
</div>
|
17 |
+
</div>
|
18 |
+
|
19 |
+
## GraySwanAI/Llama-3-8B-Instruct-RR - GGUF
|
20 |
+
|
21 |
+
This repo contains GGUF format model files for [GraySwanAI/Llama-3-8B-Instruct-RR](https://huggingface.co/GraySwanAI/Llama-3-8B-Instruct-RR).
|
22 |
+
|
23 |
+
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).
|
24 |
+
|
25 |
+
<div style="text-align: left; margin: 20px 0;">
|
26 |
+
<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;">
|
27 |
+
Run them on the TensorBlock client using your local machine ↗
|
28 |
+
</a>
|
29 |
+
</div>
|
30 |
+
|
31 |
+
## Prompt template
|
32 |
+
|
33 |
+
```
|
34 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
35 |
+
|
36 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
37 |
+
|
38 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
39 |
+
```
|
40 |
+
|
41 |
+
## Model file specification
|
42 |
+
|
43 |
+
| Filename | Quant type | File Size | Description |
|
44 |
+
| -------- | ---------- | --------- | ----------- |
|
45 |
+
| [Llama-3-8B-Instruct-RR-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
|
46 |
+
| [Llama-3-8B-Instruct-RR-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q3_K_S.gguf) | Q3_K_S | 3.664 GB | very small, high quality loss |
|
47 |
+
| [Llama-3-8B-Instruct-RR-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
|
48 |
+
| [Llama-3-8B-Instruct-RR-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
|
49 |
+
| [Llama-3-8B-Instruct-RR-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
50 |
+
| [Llama-3-8B-Instruct-RR-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
|
51 |
+
| [Llama-3-8B-Instruct-RR-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
|
52 |
+
| [Llama-3-8B-Instruct-RR-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
53 |
+
| [Llama-3-8B-Instruct-RR-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
|
54 |
+
| [Llama-3-8B-Instruct-RR-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
|
55 |
+
| [Llama-3-8B-Instruct-RR-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
|
56 |
+
| [Llama-3-8B-Instruct-RR-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-RR-GGUF/blob/main/Llama-3-8B-Instruct-RR-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
|
57 |
+
|
58 |
+
|
59 |
+
## Downloading instruction
|
60 |
+
|
61 |
+
### Command line
|
62 |
+
|
63 |
+
Firstly, install Huggingface Client
|
64 |
+
|
65 |
+
```shell
|
66 |
+
pip install -U "huggingface_hub[cli]"
|
67 |
+
```
|
68 |
+
|
69 |
+
Then, downoad the individual model file the a local directory
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/Llama-3-8B-Instruct-RR-GGUF --include "Llama-3-8B-Instruct-RR-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
73 |
+
```
|
74 |
+
|
75 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/Llama-3-8B-Instruct-RR-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
79 |
+
```
|