Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q2_K.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_L.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_M.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_S.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q4_0.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_M.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_S.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q5_0.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_M.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_S.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q6_K.gguf +3 -0
- NeuralLLaMa-3-8b-ORPO-v0.4-Q8_0.gguf +3 -0
- README.md +75 -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 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
NeuralLLaMa-3-8b-ORPO-v0.4-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:800612d789b3cf58622cb15c8c82f5ce519691562988513418819639f0701742
|
3 |
+
size 3179140768
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f5a0d3d859f2de6986136b52f920c6ce31310e8c1f8c28a99c93de2ab8cb550
|
3 |
+
size 4321966560
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e504961fd3d7c3bcba69d149635c5acb7668301c9a04ac6954d75ff2663c8dc
|
3 |
+
size 4018928096
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:829aadb614ed2740a6d941a6a49ce848da624fd7394bd9259b7f8042b0fe3f58
|
3 |
+
size 3664509408
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bdad18192a89b52698f3968e202d85e2e67255ffd0467e449de60ab8f8d9ff9
|
3 |
+
size 4661222944
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06c9c4a56bc091b293aa5843c4d88bf1d9469c9e05f243b708ec0ef1c7f52247
|
3 |
+
size 4920745504
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6f0f8de69a2cc1582076c38e5ced8af9848b5c960a45a0d34472af9e54c4cd4
|
3 |
+
size 4692680224
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17d4b8faac11d4cd85dbbab7f2bb536e12a71442b1675ba20269c1fe92f9ade7
|
3 |
+
size 5599306272
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed65a4face0d0a72de82377cf93cdeeb180ce2747c41a81f5874f569d6e26f79
|
3 |
+
size 5732999712
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2580613316fff59770947db038b9759f993d2c80551b94346b33bf6a5010c3eb
|
3 |
+
size 5599306272
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47a9f41933212b9203d70a3c3f5fbfceda53e592dd714baf7ac2de582783d659
|
3 |
+
size 6596019808
|
NeuralLLaMa-3-8b-ORPO-v0.4-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b419ca088f2f23efcf00d24a107c5f9727ccfb5ce0e864e660738e8be3a2442
|
3 |
+
size 8540788192
|
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- TensorBlock
|
6 |
+
- GGUF
|
7 |
+
base_model: Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4
|
8 |
+
---
|
9 |
+
|
10 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
11 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
12 |
+
</div>
|
13 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
14 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
15 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
16 |
+
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>
|
17 |
+
</p>
|
18 |
+
</div>
|
19 |
+
</div>
|
20 |
+
|
21 |
+
## Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4 - GGUF
|
22 |
+
|
23 |
+
This repo contains GGUF format model files for [Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4](https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4).
|
24 |
+
|
25 |
+
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).
|
26 |
+
|
27 |
+
## Prompt template
|
28 |
+
|
29 |
+
```
|
30 |
+
<|im_start|>system
|
31 |
+
{system_prompt}<|im_end|>
|
32 |
+
<|im_start|>user
|
33 |
+
{prompt}<|im_end|>
|
34 |
+
<|im_start|>assistant
|
35 |
+
```
|
36 |
+
|
37 |
+
## Model file specification
|
38 |
+
|
39 |
+
| Filename | Quant type | File Size | Description |
|
40 |
+
| -------- | ---------- | --------- | ----------- |
|
41 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
42 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
43 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
44 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
45 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
46 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
47 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
48 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
49 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
50 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
51 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
52 |
+
| [NeuralLLaMa-3-8b-ORPO-v0.4-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.4-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
53 |
+
|
54 |
+
|
55 |
+
## Downloading instruction
|
56 |
+
|
57 |
+
### Command line
|
58 |
+
|
59 |
+
Firstly, install Huggingface Client
|
60 |
+
|
61 |
+
```shell
|
62 |
+
pip install -U "huggingface_hub[cli]"
|
63 |
+
```
|
64 |
+
|
65 |
+
Then, downoad the individual model file the a local directory
|
66 |
+
|
67 |
+
```shell
|
68 |
+
huggingface-cli download tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF --include "NeuralLLaMa-3-8b-ORPO-v0.4-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
69 |
+
```
|
70 |
+
|
71 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
72 |
+
|
73 |
+
```shell
|
74 |
+
huggingface-cli download tensorblock/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
75 |
+
```
|