Lyte/Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3

Uploaded model

• NOTE: This model is just an experiment to make the model generate more tokens to do reasoning before providing an answer, with verifier and correction.
• Demo: try Q4_K_M here
• Developed by: Lyte
• License: apache-2.0
• Finetuned from model : unsloth/meta-llama-3.1-8b-instruct-bnb-4bit

Prompt

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are a world-class AI system, capable of complex reasoning and reflection and correcting your mistakes. Reason through the query/question, and then provide your final response. If you detect that you made a mistake in your reasoning at any point, correct yourself.<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{response}

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.