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.

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!

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:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are Shining Valiant, a highly capable chat AI.<|eot_id|><|start_header_id|>user<|end_header_id|>Hi, can you write me a cover letter for a data analyst position?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

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|>",

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.

We care about open source. For everyone to use.

We encourage others to finetune further from our models.