library_name: transformers
license: apache-2.0
base_model:
- grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
tags:
- generated_from_trainer
datasets:
- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
- anthracite-org/stheno-filtered-v1.1
- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
- Gryphe/Sonnet3.5-Charcard-Roleplay
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
- anthracite-org/kalo-opus-instruct-22k-no-refusal
- anthracite-org/nopm_claude_writing_fixed
- anthracite-org/kalo_opus_misc_240827
model-index:
- name: Epiculous/NovaSpark
results: []
Switching things up a bit since the last slew of models were all 12B, we now have NovaSpark! NovaSpark is an 8B model trained on GrimJim's abliterated version of arcee's SuperNova-lite. The hope is abliteration will remove some of the inherant refusals and censorship of the original model, however I noticed that finetuning on GrimJim's model undid some of the abliteration, therefore more than likely abiliteration will have to be reapplied to the resulting model to reinforce it.
Quants!
Prompting
This model is trained on llama instruct template, the prompting structure goes a little something like this:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Context and Instruct
This model is trained on llama-instruct, please use that Context and Instruct template.
Current Top Sampler Settings
Smooth Creativity: Credit to Juelsman for researching this one!
Variant Chimera: Credit to Numbra!
Spicy_Temp
Violet_Twilight-Nitral-Special