Downloads · 30 days
10
0% of all-time downloads
crestf411/L3-70B-daybreak-abliterated-v0.4
L3-70B-daybreak-abliterated-v0.4 is a text generation model from crestf411. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
Daybreak (2024 May 24) v0.4 LoRA on top of https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated
Downloads · 30 days
10
0% of all-time downloads
All-time downloads
2K
Public
Parameters
70.6B
141 GB on disk
Likes
5
Public
Click a slice to open those files.
.safetensors141 GB · 100%
From the Hugging Face model README
Daybreak (2024 May 24) v0.4 LoRA on top of https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated
Beware, depraved. Not suitable for any audience.
Dataset curation to remove slop-perceived expressions continues. Unfortunately L3-Instruct (which this is merged on top of) is riddled with "barely audible"s and "couldn't help"s and "shivers down spines" etc.
The below regexes return 0 matches, but as noted above, there are still frequent occurrences of these in the base instruct merge. Bold entries are new since v0.3.
From testing so far, it feels like temperature 0.8-0.9 is a good starting point. I have mostly tested with everything neutralized. Please give feedback on which parameters work good for you.