Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,33 @@ tags:
|
|
| 6 |
- text-generation
|
| 7 |
- autotrain_compatible
|
| 8 |
- endpoints_compatible
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
inference: false
|
| 11 |
quantized_by: Suparious
|
|
@@ -15,7 +42,21 @@ quantized_by: Suparious
|
|
| 15 |
- Model creator: [NousResearch](https://huggingface.co/NousResearch)
|
| 16 |
- Original model: [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)
|
| 17 |
|
|
|
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## How to use
|
| 21 |
|
|
|
|
| 6 |
- text-generation
|
| 7 |
- autotrain_compatible
|
| 8 |
- endpoints_compatible
|
| 9 |
+
- Llama-3
|
| 10 |
+
- instruct
|
| 11 |
+
- finetune
|
| 12 |
+
- chatml
|
| 13 |
+
- DPO
|
| 14 |
+
- RLHF
|
| 15 |
+
- gpt4
|
| 16 |
+
- synthetic data
|
| 17 |
+
- distillation
|
| 18 |
+
- function calling
|
| 19 |
+
- json mode
|
| 20 |
+
- axolotl
|
| 21 |
+
model-index:
|
| 22 |
+
- name: Hermes-2-Pro-Llama-3-8B
|
| 23 |
+
results: []
|
| 24 |
+
license: apache-2.0
|
| 25 |
+
language:
|
| 26 |
+
- en
|
| 27 |
+
datasets:
|
| 28 |
+
- teknium/OpenHermes-2.5
|
| 29 |
+
widget:
|
| 30 |
+
- example_title: Hermes 2 Pro
|
| 31 |
+
messages:
|
| 32 |
+
- role: system
|
| 33 |
+
content: You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.
|
| 34 |
+
- role: user
|
| 35 |
+
content: Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.
|
| 36 |
pipeline_tag: text-generation
|
| 37 |
inference: false
|
| 38 |
quantized_by: Suparious
|
|
|
|
| 42 |
- Model creator: [NousResearch](https://huggingface.co/NousResearch)
|
| 43 |
- Original model: [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)
|
| 44 |
|
| 45 |
+
|
| 46 |
|
| 47 |
+
## Model Description
|
| 48 |
+
|
| 49 |
+
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
|
| 50 |
+
|
| 51 |
+
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
|
| 52 |
+
|
| 53 |
+
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
|
| 54 |
+
|
| 55 |
+
This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - `<tools>`, `<tool_call>`, `<tool_response>` and their closing tags are single tokens now.
|
| 56 |
+
|
| 57 |
+
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
|
| 58 |
+
|
| 59 |
+
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
|
| 60 |
|
| 61 |
## How to use
|
| 62 |
|