|
--- |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- shining-valiant |
|
- valiant |
|
- valiant-labs |
|
- llama |
|
- llama-2 |
|
- llama-2-chat |
|
- 70b |
|
model_type: llama |
|
license: llama2 |
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
Shining Valiant is a chat model built on the Llama 2 architecture, finetuned on our data for insight, creativity, passion, and friendliness. |
|
- Uses the llama-2-70b-chat model, with safetensors |
|
- Finetuned on multiple runs across private and public data |
|
- Data focused on knowledge, enthusiasm, and structured reasoning |
|
|
|
## Version |
|
|
|
The current version is **1.1**; previous versions remain available in the repository. |
|
|
|
**1.2** is **almost done training.** |
|
|
|
Models will be released for everyone once our team's training and validation process is complete :) |
|
|
|
## Prompting |
|
Shining Valiant uses the same prompt format as Llama 2 Chat - feel free to use your existing prompts and scripts! |
|
A few examples of different formats: |
|
|
|
1. [INST] Good morning! Can you let me know how to parse a text file and turn the semicolons into commas? [/INST] |
|
|
|
2. [INST] (You are an intelligent, helpful AI assistant.) Hello, can you write me a thank you letter? [/INST] |
|
|
|
3. [INST] << SYS >>You are an intelligent, helpful AI assistant.<< /SYS >>Deep dive about a country with interesting history: [/INST] |
|
|
|
## The Model |
|
Shining Valiant is built on Llama 2's 70b parameter architecture. We've created the model through multiple finetuning runs on different compositions of our dataset. |
|
|
|
Our dataset is: |
|
|
|
|
|
70% - our custom AI instruction-tuned dataset, created and curated for increased general capability, insight, logic, depth, and specific personality |
|
|
|
|
|
30% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning, pruned through randomization and automated quality ranking |
|
|
|
|
|
|
|
We are actively working on expanding and improving this dataset for use in future releases of this model and others. |
|
|
|
|
|
|
|
 |
|
|
|
|
|
Shining Valiant is created by Valiant Labs. |
|
We care about open source. |
|
For everyone to use. |
|
|
|
We encourage others to finetune further from our models. |
