elinas commited on
Commit
626b902
1 Parent(s): dbccae8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -5
README.md CHANGED
@@ -1,14 +1,13 @@
1
  ---
2
- base_model: mistralai/Mistral-Nemo-Instruct-2407
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-Instruct-2407` which was heavily modified to produce a more coherent model, comparable to much larger models.
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. Contact me on Discord for inquiries.
 
 
 
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.