Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- argilla/OpenHermes2.5-dpo-binarized-alpha
|
5 |
+
- Locutusque/Hercules-v3.0
|
6 |
+
language:
|
7 |
+
- en
|
8 |
+
inference:
|
9 |
+
parameters:
|
10 |
+
do_sample: true
|
11 |
+
temperature: 0.8
|
12 |
+
top_p: 0.95
|
13 |
+
top_k: 40
|
14 |
+
min_new_tokens: 2
|
15 |
+
max_new_tokens: 250
|
16 |
+
repetition_penalty: 1.1
|
17 |
+
---
|
18 |
+
# NeuralReyna-Mini-1.8B-v0.2
|
19 |
+

|
20 |
+
# Description
|
21 |
+
Taken aloobun/Reyna-Mini-1.8B-v0.2 and further fine-tuned it using DPO using the argilla/OpenHermes2.5-dpo-binarized-alpha.
|
22 |
+
|
23 |
+
This model has capabilities in coding, math, science, roleplay, and function calling.
|
24 |
+
|
25 |
+
This model was trained on OpenAI's ChatML prompt format.
|
26 |
+
# Evaluation
|
27 |
+
Coming soon
|
28 |
+
|
29 |
+
# Contributions
|
30 |
+
|
31 |
+
Thanks to @aloobun and @Locutusque for their contributions to this model.
|