MN-WORDSTORM-pt8-RCM-Into-Darkness-18.5B-Instruct
This is part 8 in a 10 part series.
This version's highlights (relative to others in this 10 part series):
"Order of action within a scene is excellent, command of emotion shows in prose/characters."
(PPL = 7.7857 +/- 0.12683 @ Q4KM)
Note this model is the core model used in the new "DARKEST UNIVERSE 29B" connected with V2 of the Brainstorm 40x adapter which yeilds a model of 112 layers, 921 tensors. A beast of a creative model that excels at all levels of creativity.
Examples on the model card below:
[ https://huggingface.co/DavidAU/MN-DARKEST-UNIVERSE-29B-GGUF ]
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
For full information about this model, including:
- Details about this model and its use case(s).
- Context limits
- Special usage notes / settings.
- Any model(s) used to create this model.
- Template(s) used to access/use this model.
- Example generation(s)
- GGUF quants of this model
GGUF Quants for PT8:
Settings, Templates, Context limits etc etc are the same for all 10 in the series, you can view any below for "part 8's" information.
Also, each of the 5 below include example generations which will indicate in part this "parts" generation abilities. However there will be variations which is what this 10 parts series is really all about.
For more information on this 10 part series see one or more of these versions:
[ https://huggingface.co/DavidAU/MN-WORDSTORM-pt2-RCM-Escape-Room-18.5B-Instruct-GGUF ]
[ https://huggingface.co/DavidAU/MN-WORDSTORM-pt4-RCM-Cliffhanger-18.5B-Instruct-GGUF ]
- Downloads last month
- 20