Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q2_K.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q3_K_L.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q3_K_M.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q3_K_S.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q4_0.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q4_K_M.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q4_K_S.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q5_0.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q5_K_M.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q5_K_S.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q6_K.gguf +3 -0
- Hermes-2-Theta-Llama-3-8B-32k-Q8_0.gguf +3 -0
- README.md +108 -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 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Hermes-2-Theta-Llama-3-8B-32k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Hermes-2-Theta-Llama-3-8B-32k-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f2d48382bf80358eedfbd73679f3ae7adf73643cfda31b68c5e1678c766d88a
|
3 |
+
size 3179132000
|
Hermes-2-Theta-Llama-3-8B-32k-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:496d5db7a91ece785cee53bfd9e11f2f86094f75686862d3e1d1f108e40f61b8
|
3 |
+
size 4321956960
|
Hermes-2-Theta-Llama-3-8B-32k-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6422dcdfea3c9044554c2dcef4877fd60033260cca7c502974e7222e97befe86
|
3 |
+
size 4018918496
|
Hermes-2-Theta-Llama-3-8B-32k-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eb24bd3d036d4a0fa881ffe84567be782bd437a45db54888f30508ed538af35
|
3 |
+
size 3664499808
|
Hermes-2-Theta-Llama-3-8B-32k-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e3d38dcbe245905f728bf60b645e61479e56547b756fe53218410cbe4ef850f
|
3 |
+
size 4661212256
|
Hermes-2-Theta-Llama-3-8B-32k-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf6f58b291b10da49a61899b22098705fb840427da76253992a6cca7748ab581
|
3 |
+
size 4920734816
|
Hermes-2-Theta-Llama-3-8B-32k-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2add2e2f63d7aeca8733db16e99d2204f292b560b411a3b38b61971dd9d42b3c
|
3 |
+
size 4692669536
|
Hermes-2-Theta-Llama-3-8B-32k-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:868444fed4982393d767f5af3771e0856dc89b2e28c8b3d9b08c18ec1d3e7830
|
3 |
+
size 5599294560
|
Hermes-2-Theta-Llama-3-8B-32k-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f2a49a866d685d3189cae735c4207c8fcd2055310951e0e3845247b895ec470
|
3 |
+
size 5732988000
|
Hermes-2-Theta-Llama-3-8B-32k-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae27853ebe67161bd739c2c924d0b9bbce383c026d75c78513c4bf63e5becd2d
|
3 |
+
size 5599294560
|
Hermes-2-Theta-Llama-3-8B-32k-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f20a128c7d93a16b8fa6bfbf4a019580691dfd210cedad0c9cc7621d7756e62f
|
3 |
+
size 6596007008
|
Hermes-2-Theta-Llama-3-8B-32k-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa8585900b7e93b580a6167a86aba845847d26c78ea2f39e5a4ba908673493e6
|
3 |
+
size 8540771424
|
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: OpenPipe/Hermes-2-Theta-Llama-3-8B-32k
|
3 |
+
tags:
|
4 |
+
- Llama-3
|
5 |
+
- instruct
|
6 |
+
- finetune
|
7 |
+
- chatml
|
8 |
+
- DPO
|
9 |
+
- RLHF
|
10 |
+
- gpt4
|
11 |
+
- synthetic data
|
12 |
+
- distillation
|
13 |
+
- function calling
|
14 |
+
- json mode
|
15 |
+
- axolotl
|
16 |
+
- merges
|
17 |
+
- TensorBlock
|
18 |
+
- GGUF
|
19 |
+
language:
|
20 |
+
- en
|
21 |
+
datasets:
|
22 |
+
- teknium/OpenHermes-2.5
|
23 |
+
widget:
|
24 |
+
- example_title: Hermes 2 Pro Llama-3 Instruct Merge
|
25 |
+
messages:
|
26 |
+
- role: system
|
27 |
+
content: You are a sentient, superintelligent artificial general intelligence,
|
28 |
+
here to teach and assist me.
|
29 |
+
- role: user
|
30 |
+
content: Write a short story about Goku discovering kirby has teamed up with Majin
|
31 |
+
Buu to destroy the world.
|
32 |
+
model-index:
|
33 |
+
- name: Hermes-2-Pro-Llama-3-Instruct-8B-Merge
|
34 |
+
results: []
|
35 |
+
---
|
36 |
+
|
37 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
38 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
39 |
+
</div>
|
40 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
41 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
42 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
43 |
+
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>
|
44 |
+
</p>
|
45 |
+
</div>
|
46 |
+
</div>
|
47 |
+
|
48 |
+
## OpenPipe/Hermes-2-Theta-Llama-3-8B-32k - GGUF
|
49 |
+
|
50 |
+
This repo contains GGUF format model files for [OpenPipe/Hermes-2-Theta-Llama-3-8B-32k](https://huggingface.co/OpenPipe/Hermes-2-Theta-Llama-3-8B-32k).
|
51 |
+
|
52 |
+
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).
|
53 |
+
|
54 |
+
<div style="text-align: left; margin: 20px 0;">
|
55 |
+
<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;">
|
56 |
+
Run them on the TensorBlock client using your local machine ↗
|
57 |
+
</a>
|
58 |
+
</div>
|
59 |
+
|
60 |
+
## Prompt template
|
61 |
+
|
62 |
+
```
|
63 |
+
<|begin_of_text|><|im_start|>system
|
64 |
+
{system_prompt}<|im_end|>
|
65 |
+
<|im_start|>user
|
66 |
+
{prompt}<|im_end|>
|
67 |
+
<|im_start|>assistant
|
68 |
+
```
|
69 |
+
|
70 |
+
## Model file specification
|
71 |
+
|
72 |
+
| Filename | Quant type | File Size | Description |
|
73 |
+
| -------- | ---------- | --------- | ----------- |
|
74 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q2_K.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
|
75 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q3_K_S.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q3_K_S.gguf) | Q3_K_S | 3.664 GB | very small, high quality loss |
|
76 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q3_K_M.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
|
77 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q3_K_L.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
|
78 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q4_0.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
79 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q4_K_S.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
|
80 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q4_K_M.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
|
81 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q5_0.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
82 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q5_K_S.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
|
83 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q5_K_M.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
|
84 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q6_K.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
|
85 |
+
| [Hermes-2-Theta-Llama-3-8B-32k-Q8_0.gguf](https://huggingface.co/tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF/blob/main/Hermes-2-Theta-Llama-3-8B-32k-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
|
86 |
+
|
87 |
+
|
88 |
+
## Downloading instruction
|
89 |
+
|
90 |
+
### Command line
|
91 |
+
|
92 |
+
Firstly, install Huggingface Client
|
93 |
+
|
94 |
+
```shell
|
95 |
+
pip install -U "huggingface_hub[cli]"
|
96 |
+
```
|
97 |
+
|
98 |
+
Then, downoad the individual model file the a local directory
|
99 |
+
|
100 |
+
```shell
|
101 |
+
huggingface-cli download tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF --include "Hermes-2-Theta-Llama-3-8B-32k-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
102 |
+
```
|
103 |
+
|
104 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
105 |
+
|
106 |
+
```shell
|
107 |
+
huggingface-cli download tensorblock/Hermes-2-Theta-Llama-3-8B-32k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
108 |
+
```
|