|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
tags: |
|
- creative |
|
- creative writing |
|
- fiction writing |
|
- plot generation |
|
- sub-plot generation |
|
- fiction writing |
|
- story generation |
|
- scene continue |
|
- storytelling |
|
- fiction story |
|
- story |
|
- writing |
|
- fiction |
|
- roleplaying |
|
- swearing |
|
- rp |
|
- horror |
|
- llama3 |
|
- mergekit |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
L3-SthenoMaidBlackroot-12.2B-V1-INSTRUCT-ULTRA |
|
|
|
Merge of SthenoMaidBlackroot (8b) with Llama3 Instruct (8b) creating a model at 12.2B to improve instruction following and output. |
|
|
|
Story / Scene / Fiction: |
|
|
|
Unique "pre-amble" / "foreshadowing" of events before they happen instead of "immediate and into the fire" type prose. |
|
|
|
Some improvement in logic/problem solving relative to SMB 8B. |
|
|
|
This is an "Ultra Quality" source float32 -> GGUF transfer. |
|
|
|
The F32 version exhibits even stronger creativity (detail, place, "there") , but slightly less logic/problem solving |
|
relative to the F16 version (at a different repo). |
|
|
|
Details: |
|
|
|
- Requires Llama 3 Template and/or Command-R Template |
|
- Context 8192, with rope 32K or higher. |
|
- No special settings. |
|
|
|
Quants uploading, detailed model card update / with examples pending. |
