Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,42 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- NousResearch/Hermes-2-Pro-Mistral-7B
|
4 |
+
- kunkworksAI/BakLLaVA-1
|
5 |
+
tags:
|
6 |
+
- Mistral
|
7 |
+
- instruct
|
8 |
+
- finetune
|
9 |
+
- chatml
|
10 |
+
- DPO
|
11 |
+
- RLHF
|
12 |
+
- gpt4
|
13 |
+
- synthetic data
|
14 |
+
- distillation
|
15 |
+
- function calling
|
16 |
+
- json mode
|
17 |
+
- llava
|
18 |
+
- vision
|
19 |
+
- multimodal
|
20 |
+
model-index:
|
21 |
+
- name: Hermes-2-Pro-Mistral-7B
|
22 |
+
results: []
|
23 |
license: apache-2.0
|
24 |
+
language:
|
25 |
+
- en
|
26 |
+
datasets:
|
27 |
+
- teknium/OpenHermes-2.5
|
28 |
+
- SkunkworksAI/BakLLaVA-1-FT
|
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 |
---
|
37 |
+
|
38 |
+
# Hermes 2 Pro BakLLaVA - Mistral 7B
|
39 |
+
|
40 |
+
Hermes 2 Pro's LLaMA weights + BakLLaVA's mm_projector & vision_tower weights.
|
41 |
+
|
42 |
+
Good QA + Function Calling + JSON Mode + Vision Multimodal
|