ZhangShenao/SELM-Llama-3-8B-Instruct-iter-3
SELM-Llama-3-8B-Instruct-iter-3 is an 8 billion parameter Llama3-instruct-based Self-Exploring Language Model (SELM) developed by ZhangShenao. This model is the third iteration, fine-tuned using synthetic data derived from the HuggingFaceH4/ultrafeedback_binarized dataset. It demonstrates improved performance on benchmarks like MT-Bench compared to its predecessors and the base Llama-3-8B-Instruct model, making it suitable for instruction-following tasks.
Loading preview...
SELM-Llama-3-8B-Instruct-iter-3 Overview
This model, developed by ZhangShenao, is the third iteration of a Self-Exploring Language Model (SELM) based on the 8 billion parameter Llama-3-Instruct architecture. It is fine-tuned using synthetic data generated from the HuggingFaceH4/ultrafeedback_binarized dataset, building upon its predecessor, SELM-Llama-3-8B-Instruct-iter-2.
Key Capabilities & Performance
SELM-Llama-3-8B-Instruct-iter-3 shows enhanced performance in instruction-following and general conversational abilities. Notable results include:
- MT-Bench (Average): Achieves 8.29, surpassing SELM-Llama-3-8B-Instruct-iter-2 (8.09) and the base Meta-Llama-3-8B-Instruct (7.93).
- AlpacaEval 2.0 (LC WR): Scores 33.47.
- Ranks highly on the WildBench leaderboard.
This model is part of a research effort on "Self-Exploring Language Models: Active Preference Elicitation for Online Alignment," indicating its development focuses on advanced alignment techniques. It is licensed under MIT.
When to Use This Model
- Instruction Following: Ideal for applications requiring robust responses to user instructions.
- General Conversational AI: Suitable for chatbots and interactive agents where strong dialogue capabilities are needed.
- Research in Alignment: Useful for exploring models developed with active preference elicitation and online alignment strategies.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.