Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer
An iterative improvement of Genetic Lemonade Unleashed v2.1
This should be a direct improvement of 2.1. Uses an expanded dataset, but the training method and distribution of content within the dataset remains the same.
Compared to v3, this model never went through the DPO training and should have better prose (possibly better creativity too) but worse instruction following.
Quants:
GGUF: https://huggingface.co/mradermacher/L3.3-GeneticLemonade-Unleashed-v2.2-70B-i1-GGUF (mradermacher)
EXL2 (4.5bpw): https://huggingface.co/ApocalypseParty/L3.3-GeneticLemonade-Unleashed-v2.2-70B_4.5bpw-hb6-exl2
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ApocalypseParty/L3.3-GeneticLemonade-Unleashed-v2.2-70B_4.5bpw-hb6-exl2
Base model
zerofata/L3.3-GeneticLemonade-Unleashed-70B