initial

README.md

@@ -0,0 +1,50 @@
+---
+inference: false
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- shining-valiant
+- valiant
+- valiant-labs
+- llama
+- llama-2
+model_type: llama
+license: llama2
+---
+
+<!-- header start -->
+<!-- header end -->
+
+# Shining Valiant
+
+Shining Valiant is a chat model built on the Llama 2 architecture, finetuned on our data for insight, creativity, passion, and friendship.
+
+(70b parameters, safetensors format)
+
+## 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] Good morning! Can you let me know how to parse a text file and turn the semicolons into commas? [/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:
+75% - our custom AI instruction-tuned dataset, created and curated for increased general capability, insight, logic, depth, and specific personality
+25% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning
+
+We are actively working on expanding and improving this dataset for use in future releases of this model and others.
+
+## Who We Are
+Shining Valiant is created by Valiant Labs.
+We care about open source.
+We make software thinking open source. 
+For everyone to use.
+
+We encourage others to finetune further from our models.