Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ library_name: transformers
|
|
15 |
![image/webp](https://cdn-uploads.huggingface.co/production/uploads/630417380907b9a115c6aa9f/3hc8zt8fzKdO3qHK1p1mW.webp)
|
16 |
|
17 |
Chronos Gold 12B 1.0 is a very unique model that applies to domain areas such as
|
18 |
-
|
19 |
sequence length of 16384 (16k) and will still retain the *apparent* 128k context length from Mistral-Nemo, though it deteriorates over time like regular Nemo does based on
|
20 |
the [RULER Test](https://github.com/hsiehjackson/RULER?tab=readme-ov-file#-ruler-whats-the-real-context-size-of-your-long-context-language-models)
|
21 |
|
@@ -39,7 +39,7 @@ A system prompt describing how you'd like your bot to act.<|im_end|>
|
|
39 |
<|im_start|>user
|
40 |
Hello there!<|im_end|>
|
41 |
<|im_start|>assistant
|
42 |
-
I can assist you or we can
|
43 |
<|im_start|>user
|
44 |
I was wondering how transformers work?<|im_end|>
|
45 |
<|im_start|>assistant
|
|
|
15 |
![image/webp](https://cdn-uploads.huggingface.co/production/uploads/630417380907b9a115c6aa9f/3hc8zt8fzKdO3qHK1p1mW.webp)
|
16 |
|
17 |
Chronos Gold 12B 1.0 is a very unique model that applies to domain areas such as
|
18 |
+
general chatbot functionatliy, *roleplay*, and storywriting. The model has been observed to write up to 2250 tokens in a single sequence. The model was trained at a
|
19 |
sequence length of 16384 (16k) and will still retain the *apparent* 128k context length from Mistral-Nemo, though it deteriorates over time like regular Nemo does based on
|
20 |
the [RULER Test](https://github.com/hsiehjackson/RULER?tab=readme-ov-file#-ruler-whats-the-real-context-size-of-your-long-context-language-models)
|
21 |
|
|
|
39 |
<|im_start|>user
|
40 |
Hello there!<|im_end|>
|
41 |
<|im_start|>assistant
|
42 |
+
I can assist you or we can discuss other things?<|im_end|>
|
43 |
<|im_start|>user
|
44 |
I was wondering how transformers work?<|im_end|>
|
45 |
<|im_start|>assistant
|