Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,13 @@
|
|
1 |
---
|
2 |
-
base_model: mistralai/Mistral-Nemo-
|
3 |
license: cc-by-nc-4.0
|
4 |
-
language:
|
5 |
-
- en
|
6 |
tags:
|
7 |
- general-purpose
|
8 |
- roleplay
|
9 |
- storywriting
|
10 |
- merge
|
11 |
- finetune
|
|
|
12 |
---
|
13 |
|
14 |
# Chronos Gold 12B 1.0
|
@@ -16,7 +15,7 @@ tags:
|
|
16 |
Chronos Gold 12B 1.0 is a very unique model that applies to domains areas such as
|
17 |
geneal chatbot functionatliy, *roleplay*, and storywriting. The model has been observed to write up to 2250 tokens in a single sequence.
|
18 |
|
19 |
-
The base model is `mistralai/Mistral-Nemo-
|
20 |
|
21 |
**Chronos Gold 12B 1.0** re-creates the uniqueness of the original Chronos with significiantly enhanced prompt adherence (following), coherence, a modern dataset, as well as supporting a majority of "character card" formats in applications like SillyTavern.
|
22 |
|
@@ -24,6 +23,22 @@ It went through an intelligent merge process as my previous models and was furth
|
|
24 |
|
25 |
The specifics of the model will not be disclosed at the time due to dataset ownership.
|
26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
## Quantization
|
28 |
|
29 |
None at the momen, we will get them uploaded soon. If you create quantizations in EXL2 or LCPP then please make a post under the community tab, or contact me via discord.
|
@@ -32,4 +47,6 @@ This model was created by **elinas** on discord.
|
|
32 |
|
33 |
This is one of multiple models to come out in the series by size and model architecture, so look forward to it!
|
34 |
|
35 |
-
Please be mindful of the license. This is strictly non-commercial, but free to use at your own leisure personally.
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: mistralai/Mistral-Nemo-Base-2407
|
3 |
license: cc-by-nc-4.0
|
|
|
|
|
4 |
tags:
|
5 |
- general-purpose
|
6 |
- roleplay
|
7 |
- storywriting
|
8 |
- merge
|
9 |
- finetune
|
10 |
+
library_name: transformers
|
11 |
---
|
12 |
|
13 |
# Chronos Gold 12B 1.0
|
|
|
15 |
Chronos Gold 12B 1.0 is a very unique model that applies to domains areas such as
|
16 |
geneal chatbot functionatliy, *roleplay*, and storywriting. The model has been observed to write up to 2250 tokens in a single sequence.
|
17 |
|
18 |
+
The base model is `mistralai/Mistral-Nemo-Base-2407` which was heavily modified to produce a more coherent model, comparable to much larger models.
|
19 |
|
20 |
**Chronos Gold 12B 1.0** re-creates the uniqueness of the original Chronos with significiantly enhanced prompt adherence (following), coherence, a modern dataset, as well as supporting a majority of "character card" formats in applications like SillyTavern.
|
21 |
|
|
|
23 |
|
24 |
The specifics of the model will not be disclosed at the time due to dataset ownership.
|
25 |
|
26 |
+
## Instruct Template
|
27 |
+
|
28 |
+
This model uses `ChatML` - below is an example. It is a preset in many frontends.
|
29 |
+
|
30 |
+
```
|
31 |
+
<|im_start|>system
|
32 |
+
A system prompt describing how you'd like your bot to act.<|im_end|>
|
33 |
+
<|im_start|>user
|
34 |
+
Hello there!<|im_end|>
|
35 |
+
<|im_start|>assistant
|
36 |
+
I can assist you or we can disucss other things?<|im_end|>
|
37 |
+
<|im_start|>user
|
38 |
+
I was wondering how transformers work?<|im_end|>
|
39 |
+
<|im_start|>assistant
|
40 |
+
```
|
41 |
+
|
42 |
## Quantization
|
43 |
|
44 |
None at the momen, we will get them uploaded soon. If you create quantizations in EXL2 or LCPP then please make a post under the community tab, or contact me via discord.
|
|
|
47 |
|
48 |
This is one of multiple models to come out in the series by size and model architecture, so look forward to it!
|
49 |
|
50 |
+
Please be mindful of the license. This is strictly non-commercial, but free to use at your own leisure personally. Outputs generated by the model are not reflective of my views.
|
51 |
+
|
52 |
+
Contact me on Discord for inquiries.
|