license: other
language:
- en
UPDATE: There's a Llama 2 sequel now! Check it out here!
An experiment with gradient merges using the following script, with Chronos as its primary model, augmented by Hermes and Wizard-Vicuna Uncensored.
Quantized models are available from TheBloke: GGML - GPTQ (You're the best!)
Model details
Chronos is a wonderfully verbose model, though it definitely seems to lack in the logic department. Hermes and WizardLM have been merged gradually, primarily in the higher layers (10+) in an attempt to rectify some of this behaviour.
The main objective was to create an all-round model with improved story generation and roleplaying capabilities.
Below is an illustration to showcase a rough approximation of the gradients I used to create MythoLogic:
Prompt Format
This model primarily uses Alpaca formatting, so for optimal model performance, use:
<System prompt/Character Card>
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
license: other
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 47.23 |
| ARC (25-shot) | 58.45 |
| HellaSwag (10-shot) | 81.56 |
| MMLU (5-shot) | 49.36 |
| TruthfulQA (0-shot) | 49.47 |
| Winogrande (5-shot) | 75.61 |
| GSM8K (5-shot) | 8.64 |
| DROP (3-shot) | 7.53 |