Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q2_K.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_L.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_M.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_S.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_0.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_M.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_S.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_0.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_S.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q6_K.gguf +3 -0
- Nous-Hermes-2-Mixtral-8x7B-SFT-Q8_0.gguf +3 -0
- README.md +94 -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 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Nous-Hermes-2-Mixtral-8x7B-SFT-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1e43eef0419c3c99ce2bf2bafcc0559d407ec2740cb19e111d3945dfe9d9c02
|
3 |
+
size 17311239872
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09d58fcbb4a4fd0b98b6b1f502f558fddbe34cfffda53a38070e82c4f7ece974
|
3 |
+
size 24169656832
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4a4ba63e31e32445f700d17cf14772b8b73ae016c4331f75a62d4351d5154bd
|
3 |
+
size 22546461184
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8f28716a6a694b16f0711c2c26a5038e8b0a396dca2fa2f61f9b1fac24dc681
|
3 |
+
size 20432531968
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3afd5551bb57d8d76724a7b8e0bad94a713755ce812fc2b20d5aab52a6b3d369
|
3 |
+
size 26443601472
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdebf8deca457d397d4baba74e72b1f6f4f08e6738dc981c527f76f01163ecba
|
3 |
+
size 28448478784
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb297d122f28277b26f1b88f6fb05f7c0475024034aeb27c1f8cd17af7f92cce
|
3 |
+
size 26745591360
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb482a6dd8828c9196cf8e66268f64b0994ac41e8c9842eb9394b1acf189bcc8
|
3 |
+
size 32231348800
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b063114238a08de04345012966184cdc7926a5475358f2d9a93d44ad7463c53
|
3 |
+
size 33229593152
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03c2bd662a4fb03cefe2b4f5f9094a1418def24e5137c04d9edf8562cb33834c
|
3 |
+
size 32231348800
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:902e3af0e68cfc7aebb16f155e0a62c66c7ce83f85905276f34cbecf3b134edf
|
3 |
+
size 38380830336
|
Nous-Hermes-2-Mixtral-8x7B-SFT-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb67b4613c51ce85df18fe72a5efb135cc3e896fe4a31ca55aae96bb18e9301a
|
3 |
+
size 49626336768
|
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT
|
3 |
+
tags:
|
4 |
+
- Mixtral
|
5 |
+
- instruct
|
6 |
+
- finetune
|
7 |
+
- chatml
|
8 |
+
- gpt4
|
9 |
+
- synthetic data
|
10 |
+
- distillation
|
11 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
license: apache-2.0
|
14 |
+
language:
|
15 |
+
- en
|
16 |
+
datasets:
|
17 |
+
- teknium/OpenHermes-2.5
|
18 |
+
model-index:
|
19 |
+
- name: Nous-Hermes-2-Mixtral-8x7B-SFT
|
20 |
+
results: []
|
21 |
+
---
|
22 |
+
|
23 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
24 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
25 |
+
</div>
|
26 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
27 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
28 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
29 |
+
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>
|
30 |
+
</p>
|
31 |
+
</div>
|
32 |
+
</div>
|
33 |
+
|
34 |
+
## NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT - GGUF
|
35 |
+
|
36 |
+
This repo contains GGUF format model files for [NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT).
|
37 |
+
|
38 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
39 |
+
|
40 |
+
<div style="text-align: left; margin: 20px 0;">
|
41 |
+
<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;">
|
42 |
+
Run them on the TensorBlock client using your local machine ↗
|
43 |
+
</a>
|
44 |
+
</div>
|
45 |
+
|
46 |
+
## Prompt template
|
47 |
+
|
48 |
+
```
|
49 |
+
<|im_start|>system
|
50 |
+
{system_prompt}<|im_end|>
|
51 |
+
<|im_start|>user
|
52 |
+
{prompt}<|im_end|>
|
53 |
+
<|im_start|>assistant
|
54 |
+
```
|
55 |
+
|
56 |
+
## Model file specification
|
57 |
+
|
58 |
+
| Filename | Quant type | File Size | Description |
|
59 |
+
| -------- | ---------- | --------- | ----------- |
|
60 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q2_K.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q2_K.gguf) | Q2_K | 17.311 GB | smallest, significant quality loss - not recommended for most purposes |
|
61 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_S.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_S.gguf) | Q3_K_S | 20.433 GB | very small, high quality loss |
|
62 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_M.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_M.gguf) | Q3_K_M | 22.546 GB | very small, high quality loss |
|
63 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_L.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_L.gguf) | Q3_K_L | 24.170 GB | small, substantial quality loss |
|
64 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_0.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_0.gguf) | Q4_0 | 26.444 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
65 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_S.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_S.gguf) | Q4_K_S | 26.746 GB | small, greater quality loss |
|
66 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_M.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_M.gguf) | Q4_K_M | 28.448 GB | medium, balanced quality - recommended |
|
67 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_0.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_0.gguf) | Q5_0 | 32.231 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
68 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_S.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_S.gguf) | Q5_K_S | 32.231 GB | large, low quality loss - recommended |
|
69 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf) | Q5_K_M | 33.230 GB | large, very low quality loss - recommended |
|
70 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q6_K.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q6_K.gguf) | Q6_K | 38.381 GB | very large, extremely low quality loss |
|
71 |
+
| [Nous-Hermes-2-Mixtral-8x7B-SFT-Q8_0.gguf](https://huggingface.co/tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/Nous-Hermes-2-Mixtral-8x7B-SFT-Q8_0.gguf) | Q8_0 | 49.626 GB | very large, extremely low quality loss - not recommended |
|
72 |
+
|
73 |
+
|
74 |
+
## Downloading instruction
|
75 |
+
|
76 |
+
### Command line
|
77 |
+
|
78 |
+
Firstly, install Huggingface Client
|
79 |
+
|
80 |
+
```shell
|
81 |
+
pip install -U "huggingface_hub[cli]"
|
82 |
+
```
|
83 |
+
|
84 |
+
Then, downoad the individual model file the a local directory
|
85 |
+
|
86 |
+
```shell
|
87 |
+
huggingface-cli download tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF --include "Nous-Hermes-2-Mixtral-8x7B-SFT-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
88 |
+
```
|
89 |
+
|
90 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
91 |
+
|
92 |
+
```shell
|
93 |
+
huggingface-cli download tensorblock/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
94 |
+
```
|