Hugging Face's logo

openaccess-ai-collective
/
wizard-mega-13b

Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
Inference Endpoints
Model card Files Community
10
wizard-mega-13b / README.md
winglian's picture
winglian
README.md
8c25f01
preview code
|
raw
history blame
1.13 kB
metadata
datasets:
  - anon8231489123/ShareGPT_Vicuna_unfiltered
  - ehartford/wizard_vicuna_70k_unfiltered
  - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
language:
  - en
library_name: transformers
pipeline_tag: text-generation

Wizard Mega 13B

Wizard Mega is a Llama 13B model fine-tuned on the ShareGPT, WizardLM, and Wizard-Vicuna datasets. These particular datasets have all been filtered to remove responses where the model responds with "As an AI language model...", etc or when the model refuses to respond.

Release (Epoch Two) - The Wizard Mega 13B model is being released after two epochs as the eval loss increased during the 3rd (final planned epoch). Because of this, we have preliminarily decided to use the epoch 2 checkpoint as the final release candidate. https://wandb.ai/wing-lian/vicuna-13b/runs/5uebgm49

Build

Wizard Mega was built with Axolotl on 8xA100 80GB for 15 hours. The configuration to duplicate this build is provided in this repo's /config folder.