Eleuther Pythia6.9b Hh Sft
A causal language model based on the Pythia-6.9b foundation model, fine-tuned using Anthropic's hh-rlhf dataset for supervised training
Downloads 58
Release Time : 8/7/2023
Model Overview
This is a 6.9B parameter-scale causal language model, fine-tuned with RLHF (Reinforcement Learning from Human Feedback), suitable for dialogue generation and text completion tasks
Model Features
RLHF Fine-tuning
Supervised fine-tuning using Anthropic's hh-rlhf dataset enhances the model's alignment with human preferences
Large Parameter Scale
6.9B parameter scale provides robust language understanding and generation capabilities
Open-source License
Apache-2.0 license allows for commercial and research use
Model Capabilities
Text generation
Dialogue generation
Text completion
Instruction following
Use Cases
Dialogue Systems
Intelligent Assistant
Build conversational assistants capable of understanding and responding to human instructions
RLHF fine-tuning enables generation of responses more aligned with human preferences
Content Creation
Creative Writing Assistance
Assist writers with creative writing and content generation
Featured Recommended AI Models