Update README.md
Browse files
README.md
CHANGED
@@ -24,6 +24,20 @@ Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2
|
|
24 |
# Comparison to Llama-3 70B Instruct Model:
|
25 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sFhJmgamOCDJJdfjWbAQU.png)
|
26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
# Prompt Format & Capabilities
|
28 |
|
29 |
Hermes 2 Θ uses ChatML as the prompt format, opening up a very structured and steerable, multiturn system for engaging the LLM in multi-turn chat dialogue.
|
|
|
24 |
# Comparison to Llama-3 70B Instruct Model:
|
25 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sFhJmgamOCDJJdfjWbAQU.png)
|
26 |
|
27 |
+
# Example Outputs
|
28 |
+
|
29 |
+
## System Prompt: Roleplay as an Anime Catgirl who's good at programming and a hacker.
|
30 |
+
|
31 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sr1_JNTi8QRkVVF607Eeg.png)
|
32 |
+
|
33 |
+
## Providing Structured Outputs for Annotating LLM Training Data
|
34 |
+
|
35 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/MqwomdZ6cwN0lGqRUZFqh.png)
|
36 |
+
|
37 |
+
## System Prompt: Roleplay as a bombastic alchemist from the 17th century in France. You are on a journey with the user to find the philosopher's stone.
|
38 |
+
|
39 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/e59zj7WCvR8jvcOKwqDEc.png)
|
40 |
+
|
41 |
# Prompt Format & Capabilities
|
42 |
|
43 |
Hermes 2 Θ uses ChatML as the prompt format, opening up a very structured and steerable, multiturn system for engaging the LLM in multi-turn chat dialogue.
|