Neelectric/Llama-3.1-8B-Instruct_SFT_Chat-220kv00.04
Neelectric/Llama-3.1-8B-Instruct_SFT_Chat-220kv00.04 is an 8 billion parameter instruction-tuned causal language model developed by Neelectric. It is a fine-tuned version of Meta's Llama-3.1-8B-Instruct, specifically optimized for chat applications. This model leverages a 32768 token context length and is trained using Supervised Fine-Tuning (SFT) on the Neelectric/Dolci-Think-SFT-7B_persona-if_Llama3_4096toks dataset, making it suitable for conversational AI tasks.
Loading preview...
Neelectric/Llama-3.1-8B-Instruct_SFT_Chat-220kv00.04 Overview
This model is an 8 billion parameter instruction-tuned language model developed by Neelectric. It is built upon Meta's Llama-3.1-8B-Instruct base model and has been further fine-tuned using Supervised Fine-Tuning (SFT) techniques. The training utilized the Neelectric/Dolci-Think-SFT-7B_persona-if_Llama3_4096toks dataset, focusing on enhancing its conversational capabilities.
Key Capabilities
- Instruction Following: Designed to accurately follow user instructions in a conversational context.
- Chat Optimization: Specifically fine-tuned for chat-based interactions, making it suitable for dialogue systems.
- Extended Context: Supports a substantial context length of 32768 tokens, allowing for more coherent and extended conversations.
Training Details
The model was trained using the TRL (Transformers Reinforcement Learning) library, version 0.28.0.dev0. This SFT approach aims to align the model's outputs with desired conversational patterns and responses. The training process can be visualized via Weights & Biases, as indicated in the original model card.