ValiantLabs/Llama3-70B-ShiningValiant2

Shining Valiant 2 is a chat model built on Llama 3 70b, finetuned on our data for friendship, insight, knowledge and enthusiasm.

Finetuned on meta-llama/Meta-Llama-3-70B-Instruct for best available general performance
Trained on our data, focused on science, engineering, technical knowledge, and structured reasoning

Version

This is the 2024-04-20 release of Shining Valiant 2 for Llama 3 70b.

We're working on more Llama 3 releases to come, including Shining Valiant and our Build Tools set of models. We're excited to bring these to everyone soon!

Prompting Guide

Shining Valiant 2 uses the Llama 3 Instruct prompt format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{{ model_answer_1 }}<|eot_id|>

Example input:

WARNING: text-generation-webui

When using Llama 3 Instruct models (including Shining Valiant 2) with text-generation-webui note that a current bug in webui can result in incorrect reading of the model's ending tokens, causing unfinished outputs and incorrect structure.

For a temporary workaround if you encounter this issue, edit Shining Valiant 2's tokenizer_config file as indicated:

from "eos_token": "<|end_of_text|>",

to "eos_token": "<|eot_id|>",

The Model

Shining Valiant 2 is built on top of Llama 3 70b Instruct, the highest performance open-source model currently available.

Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!

Shining Valiant 2 is created by Valiant Labs.

Check out our HuggingFace page to see all of our models!

We care about open source. For everyone to use.

We encourage others to finetune further from our models.