Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf +3 -0
- DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf +3 -0
- README.md +109 -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 |
+
DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a325a034b1e182938ae2a536b14febc88032958a2eb45d497d5e451ac65d39
|
3 |
+
size 3179137664
|
DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2c6628ddf9f614cbc55d9af08c0d8f1d02ff7003d62d734b7e3295e6d9f0701
|
3 |
+
size 4321962624
|
DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7586500237fc8c5d8f2972bd928eeed4df15ceafba51984f97697fefb3785da
|
3 |
+
size 4018924160
|
DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf86d886ad20c42c491d6a409545bc61afc41b613dc165d48ae2bde3b59ba387
|
3 |
+
size 3664505472
|
DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd32e18873f21c665e60f466e4a49159c34b2f1bcd66e7c0a90999027e67a212
|
3 |
+
size 4661217920
|
DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11870b66a8e1faa9020b8a26bdf1b9b7bcf70ff8f28b8e5a95cd5ef202e807c1
|
3 |
+
size 4920740480
|
DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f70b7b0f7e898ce80746f5cae0694190dc81a833f3e092e4b76fbe8bc788756
|
3 |
+
size 4692675200
|
DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:841944a025994ad88b7a4b48866b5e87661afa572315ed3639bbaaa03f4900de
|
3 |
+
size 5599300224
|
DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b56f92e50040e5b66ba7d1e20de0a8a674e27f11ce18fe0b34fb5b5e13e87ed
|
3 |
+
size 5732993664
|
DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a3430e8f1eeef081f3410c72045b5fed8cde15af15460c43a307c429cda011f
|
3 |
+
size 5599300224
|
DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cb138f445b6c9e39bbe67d4cd82f91960d3943c411b015751b1279b13218a2d
|
3 |
+
size 6596012672
|
DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3edf79cb8b4eec74a64ca7c946949bdc3f571686d3d13a287b31071b197835a6
|
3 |
+
size 8540777088
|
README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: llama3
|
5 |
+
tags:
|
6 |
+
- Llama-3
|
7 |
+
- instruct
|
8 |
+
- finetune
|
9 |
+
- chatml
|
10 |
+
- gpt4
|
11 |
+
- synthetic data
|
12 |
+
- distillation
|
13 |
+
- function calling
|
14 |
+
- json mode
|
15 |
+
- axolotl
|
16 |
+
- roleplaying
|
17 |
+
- chat
|
18 |
+
- reasoning
|
19 |
+
- r1
|
20 |
+
- vllm
|
21 |
+
- TensorBlock
|
22 |
+
- GGUF
|
23 |
+
base_model: NousResearch/DeepHermes-3-Llama-3-8B-Preview
|
24 |
+
widget:
|
25 |
+
- example_title: Hermes 3
|
26 |
+
messages:
|
27 |
+
- role: system
|
28 |
+
content: You are a sentient, superintelligent artificial general intelligence,
|
29 |
+
here to teach and assist me.
|
30 |
+
- role: user
|
31 |
+
content: What is the meaning of life?
|
32 |
+
library_name: transformers
|
33 |
+
model-index:
|
34 |
+
- name: DeepHermes-3-Llama-3.1-8B
|
35 |
+
results: []
|
36 |
+
---
|
37 |
+
|
38 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
39 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
40 |
+
</div>
|
41 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
42 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
43 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
44 |
+
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>
|
45 |
+
</p>
|
46 |
+
</div>
|
47 |
+
</div>
|
48 |
+
|
49 |
+
## NousResearch/DeepHermes-3-Llama-3-8B-Preview - GGUF
|
50 |
+
|
51 |
+
This repo contains GGUF format model files for [NousResearch/DeepHermes-3-Llama-3-8B-Preview](https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview).
|
52 |
+
|
53 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4658](https://github.com/ggerganov/llama.cpp/commit/855cd0734aca26c86cc23d94aefd34f934464ac9).
|
54 |
+
|
55 |
+
<div style="text-align: left; margin: 20px 0;">
|
56 |
+
<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;">
|
57 |
+
Run them on the TensorBlock client using your local machine ↗
|
58 |
+
</a>
|
59 |
+
</div>
|
60 |
+
|
61 |
+
## Prompt template
|
62 |
+
|
63 |
+
```
|
64 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
65 |
+
|
66 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
67 |
+
|
68 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
69 |
+
```
|
70 |
+
|
71 |
+
## Model file specification
|
72 |
+
|
73 |
+
| Filename | Quant type | File Size | Description |
|
74 |
+
| -------- | ---------- | --------- | ----------- |
|
75 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
|
76 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
|
77 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
|
78 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
|
79 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
80 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
|
81 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
|
82 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
83 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
|
84 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
|
85 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
|
86 |
+
| [DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf](https://huggingface.co/tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
|
87 |
+
|
88 |
+
|
89 |
+
## Downloading instruction
|
90 |
+
|
91 |
+
### Command line
|
92 |
+
|
93 |
+
Firstly, install Huggingface Client
|
94 |
+
|
95 |
+
```shell
|
96 |
+
pip install -U "huggingface_hub[cli]"
|
97 |
+
```
|
98 |
+
|
99 |
+
Then, downoad the individual model file the a local directory
|
100 |
+
|
101 |
+
```shell
|
102 |
+
huggingface-cli download tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF --include "DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
103 |
+
```
|
104 |
+
|
105 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
106 |
+
|
107 |
+
```shell
|
108 |
+
huggingface-cli download tensorblock/DeepHermes-3-Llama-3-8B-Preview-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
109 |
+
```
|