Llamacpp quants
Browse files- .gitattributes +12 -0
- Hermes-2-Pro-Mistral-7B-Q2_K.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q3_K_L.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q3_K_M.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q3_K_S.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q4_0.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q4_K_M.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q4_K_S.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q5_0.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q5_K_M.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q5_K_S.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q6_K.gguf +3 -0
- Hermes-2-Pro-Mistral-7B-Q8_0.gguf +3 -0
- README.md +57 -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-Pro-Mistral-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Hermes-2-Pro-Mistral-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Hermes-2-Pro-Mistral-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Hermes-2-Pro-Mistral-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Hermes-2-Pro-Mistral-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Hermes-2-Pro-Mistral-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Hermes-2-Pro-Mistral-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Hermes-2-Pro-Mistral-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Hermes-2-Pro-Mistral-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Hermes-2-Pro-Mistral-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Hermes-2-Pro-Mistral-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Hermes-2-Pro-Mistral-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Hermes-2-Pro-Mistral-7B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e46bbf4a06ff7f83d0c08f588c40a07f4c717f17a160d7922b25170d28e94f1
|
3 |
+
size 2719393536
|
Hermes-2-Pro-Mistral-7B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d008d815ccb616630cc225e0ee81ba02a9c926ce6c433734d219f3022e1bcf6
|
3 |
+
size 3822189312
|
Hermes-2-Pro-Mistral-7B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed411da9723ce4165a500f5cfe6f62a42de5f01dc9db94b3f79b0e6d69fdddae
|
3 |
+
size 3519150848
|
Hermes-2-Pro-Mistral-7B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb5f6ce63e532f11578de2f064326f4a00dc9d07fb3d13288839ee8426ae783b
|
3 |
+
size 3164732160
|
Hermes-2-Pro-Mistral-7B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8623bc923fa07022a6df5487cc5d8fd3913a5162a480373b51c8446b80d84b2
|
3 |
+
size 4109098752
|
Hermes-2-Pro-Mistral-7B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1eac044564019481d5be58fa1c67579d41a9d4d3324a6803327818b96fdfd747
|
3 |
+
size 4368621312
|
Hermes-2-Pro-Mistral-7B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b891fa8b6d07562627639350aff808d29bae6d37606c55e3c76aee47583cd07
|
3 |
+
size 4140556032
|
Hermes-2-Pro-Mistral-7B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2ab246f2ee9f2046e2dcfdb5d94b9b812df91473ef4864bad1c9b7436472dd3
|
3 |
+
size 4997914368
|
Hermes-2-Pro-Mistral-7B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:427f2dcfa6d403410f9c036cfcb00a5365717bfb44318bc5413d234c5ba0958c
|
3 |
+
size 5131607808
|
Hermes-2-Pro-Mistral-7B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:259997a82718b616a1b4e5b8d79fd948cf3b3dabc849a8ec7f0ea4527016b912
|
3 |
+
size 4997914368
|
Hermes-2-Pro-Mistral-7B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3999d974f1d86c54dd4acfb4c784b50afeaeb7e76c7586829519ef12212626d5
|
3 |
+
size 5942280960
|
Hermes-2-Pro-Mistral-7B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:107d9516acb6a1f879b1fbfa283b399529ee0518b95b632c6a624b109ff9cdbf
|
3 |
+
size 7696136960
|
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: mistralai/Mistral-7B-v0.1
|
3 |
+
tags:
|
4 |
+
- Mistral
|
5 |
+
- instruct
|
6 |
+
- finetune
|
7 |
+
- chatml
|
8 |
+
- DPO
|
9 |
+
- RLHF
|
10 |
+
- gpt4
|
11 |
+
- synthetic data
|
12 |
+
- distillation
|
13 |
+
- function calling
|
14 |
+
- json mode
|
15 |
+
model-index:
|
16 |
+
- name: Hermes-2-Pro-Mistral-7B
|
17 |
+
results: []
|
18 |
+
license: apache-2.0
|
19 |
+
language:
|
20 |
+
- en
|
21 |
+
datasets:
|
22 |
+
- teknium/OpenHermes-2.5
|
23 |
+
widget:
|
24 |
+
- example_title: Hermes 2 Pro
|
25 |
+
messages:
|
26 |
+
- role: system
|
27 |
+
content: You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.
|
28 |
+
- role: user
|
29 |
+
content: Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.
|
30 |
+
quantized_by: bartowski
|
31 |
+
pipeline_tag: text-generation
|
32 |
+
---
|
33 |
+
|
34 |
+
## Llamacpp Quantizations of Hermes-2-Pro-Mistral-7B
|
35 |
+
|
36 |
+
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2405">b2405</a> for quantization.
|
37 |
+
|
38 |
+
Original model: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B
|
39 |
+
|
40 |
+
Download a file (not the whole branch) from below:
|
41 |
+
|
42 |
+
| Filename | Quant type | File Size | Description |
|
43 |
+
| -------- | ---------- | --------- | ----------- |
|
44 |
+
| [Hermes-2-Pro-Mistral-7B-Q8_0.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
|
45 |
+
| [Hermes-2-Pro-Mistral-7B-Q6_K.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
|
46 |
+
| [Hermes-2-Pro-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
|
47 |
+
| [Hermes-2-Pro-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
|
48 |
+
| [Hermes-2-Pro-Mistral-7B-Q5_0.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
|
49 |
+
| [Hermes-2-Pro-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
|
50 |
+
| [Hermes-2-Pro-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
|
51 |
+
| [Hermes-2-Pro-Mistral-7B-Q4_0.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
|
52 |
+
| [Hermes-2-Pro-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
|
53 |
+
| [Hermes-2-Pro-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
|
54 |
+
| [Hermes-2-Pro-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
|
55 |
+
| [Hermes-2-Pro-Mistral-7B-Q2_K.gguf](https://huggingface.co/bartowski/Hermes-2-Pro-Mistral-7B-GGUF/blob/main/Hermes-2-Pro-Mistral-7B-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
|
56 |
+
|
57 |
+
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|