Josephgflowers
commited on
Commit
•
4764830
1
Parent(s):
a4794a0
Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ Model Name: Cinder
|
|
7 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6328952f798f8d122ce62a44/_5ihlDZflgdA0Em76t5j9.png)
|
8 |
|
9 |
Created by: Joseph Flowers
|
10 |
-
|
11 |
Model Overview
|
12 |
Cinder is an AI chatbot tailored for engaging users in scientific and educational conversations, offering companionship, and sparking imaginative exploration. It is built on the TinyLlama 1.1B parameter model and trained on a unique combination of datasets.
|
13 |
|
@@ -19,6 +19,8 @@ A subset of Open Orca: https://huggingface.co/datasets/Open-Orca/OpenOrcatr
|
|
19 |
Q&A content generated by GPT-3.5 Turbo by having it read open source encyclopedias and create QA pairs.
|
20 |
Shortened version of Samantha by Eric Hartford https://huggingface.co/datasets/cognitivecomputations/samantha-data
|
21 |
OpenAssistant: https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25
|
|
|
|
|
22 |
Core Influences: Inspired by the character 'Data' from Star Trek: The Next Generation, Lewis Carroll's writings, and a range of educational resources.
|
23 |
|
24 |
Key Features
|
|
|
7 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6328952f798f8d122ce62a44/_5ihlDZflgdA0Em76t5j9.png)
|
8 |
|
9 |
Created by: Joseph Flowers
|
10 |
+
***Updated 1-10-23*** New round of training, added gguf model 8bit.
|
11 |
Model Overview
|
12 |
Cinder is an AI chatbot tailored for engaging users in scientific and educational conversations, offering companionship, and sparking imaginative exploration. It is built on the TinyLlama 1.1B parameter model and trained on a unique combination of datasets.
|
13 |
|
|
|
19 |
Q&A content generated by GPT-3.5 Turbo by having it read open source encyclopedias and create QA pairs.
|
20 |
Shortened version of Samantha by Eric Hartford https://huggingface.co/datasets/cognitivecomputations/samantha-data
|
21 |
OpenAssistant: https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25
|
22 |
+
***Updated 1-10-23*** Continued training with sorted Orca dataset to around 600mb for STEM related topics, generated around 100mb of STEM q and a with GPT3.5 and GPT4,
|
23 |
+
a chunk of Samantha dataset, Glaive function calling v2, and python code instruction 18k alpaca dataset, around 1GB total.
|
24 |
Core Influences: Inspired by the character 'Data' from Star Trek: The Next Generation, Lewis Carroll's writings, and a range of educational resources.
|
25 |
|
26 |
Key Features
|