cgato/Thespis-7b-v0.2-SFTTest-3Epoch
Thespis-7b-v0.2-SFTTest-3Epoch is a test model developed by cgato, based on an unspecified 7 billion parameter architecture. This model is specifically noted for its verbosity compared to previous iterations and is intended for testing purposes. It was fine-tuned using a diverse set of external datasets including Pure-Dove, Claude Multiround 30k, OpenOrcaSlim, Augmental, ToxicQA, yahoo_answers_qa, and a cleaned chub.ai characters dataset. Its primary characteristic is its verbose output, making it potentially suitable for applications requiring detailed or extensive responses.
Loading preview...
Thespis-7b-v0.2-SFTTest-3Epoch: A Verbose Test Model
This model, developed by cgato, is presented as a test iteration, with no guarantees regarding its performance. A key characteristic noted by the developer is its increased verbosity compared to earlier models. It was fine-tuned using a comprehensive collection of external datasets, including:
- Pure-Dove Dataset
- Claude Multiround 30k
- OpenOrcaSlim
- Augmental Dataset
- ToxicQA
- yahoo_answers_qa
Additionally, it incorporated a cleaned chub.ai characters dataset, provided by kubernetes-bad. The model is configured to use a standard chat prompt format, compatible with default Ooba and Silly Tavern templates, where user input and bot responses alternate. Users should expect potential repetition in its output as the dataset is still undergoing refinement.
Key Characteristics
- Verbose Output: Designed to produce more extensive responses.
- Diverse Training Data: Fine-tuned on a wide array of conversational and QA datasets.
- Chat Format Compatibility: Optimized for common chat interfaces like Ooba and Silly Tavern.
Intended Use
- Testing and Experimentation: Primarily for evaluating model behavior and dataset impact.
- Applications Requiring Detail: Potentially useful where verbose, descriptive outputs are desired.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.