hardlyworking/AGI

hardlyworking/AGI: A Fine-Tuned 4B Parameter Model

hardlyworking/AGI is a 4 billion parameter language model, fine-tuned from the GreenerPastures/Basically-Human-4B base model. It was developed using the Axolotl framework, indicating a focus on efficient and customizable training.

Key Capabilities & Training

This model's training involved a unique blend of datasets, suggesting a specialization in certain conversational and creative text generation tasks:

• Base Model: GreenerPastures/Basically-Human-4B
• Fine-tuning Datasets:
  • jeiku/Writing: Likely enhances general writing and creative text generation abilities.
  • ResplendentAI/Sissification_Hypno_1k and ResplendentAI/Synthetic_Soul_1k: These Alpaca-style datasets suggest a focus on specific conversational styles, role-playing, or niche content generation.
• Context Length: Supports a substantial context window of 40960 tokens, allowing for processing and generating longer, more coherent texts.
• Training Hyperparameters: Utilized a learning rate of 1e-05, cosine LR scheduler, and 4 epochs, indicating a thorough fine-tuning process.

Intended Use Cases

Given its training on specialized datasets, hardlyworking/AGI is likely well-suited for:

• Creative Writing: Generating diverse forms of text, potentially with specific stylistic nuances.
• Conversational AI: Engaging in dialogue, especially in contexts aligned with its fine-tuning data.
• Niche Content Generation: Creating content for specific domains or themes present in the ResplendentAI datasets.

Users should consider the specific nature of the fine-tuning datasets when evaluating its suitability for general-purpose tasks versus specialized applications.