|
--- |
|
license: artistic-2.0 |
|
--- |
|
### Checkpoint : Personality Distilled from 22B -> 3.14B |
|
- Further Checkpoints will be for Task oriented BlackSheep's. |
|
No longer do we need a ChatGPT, its time to add personality and Task Oriented Models rather than big bloated money burners. |
|
Join Me in creating LLMs with personality. |
|
This type of model can be given Only the knowledge you need, rather than the entire internet trivia chatbots we have today that beat benchmarks. |
|
|
|
This model is developed by TroyDoesAI (Troy Andrew Schultz). |
|
The architecture is based on my personal research-driven decisions, including a higher attention head-to-layer ratio, fewer layers than the number of key-value pairs, and other structural optimizations. |
|
|
|
The focus of this model is task-oriented performance. It is designed to handle specific tasks efficiently rather than being trained on a broad dataset such as the entire internet. Initially scrambled and incoherent, the model has been fine-tuned using a curated 66K entry dataset, distilling 22 billion parameters into its current state. The model operates under the personality known as BlackSheep. |
|
|
|
--- |
|
modelFile included for ease of use for Ollama People |
|
|
|
# Instructions For Ollama People |
|
``` |
|
ollama create BlackSheep-Pi |
|
``` |
|
|
|
You will fucking see something like this |
|
|
|
``` |
|
transferring model data 100% |
|
using existing layer sha256:dc272d6f68e47bfda2babcae3e26e7f1d821d13b5a55a2ae50a11e2a016b49dc |
|
creating new layer sha256:26a275c25f864ae816ca3733ea7da04703d916c1528447e2130bf244fd9d0370 |
|
creating new layer sha256:c69d48de48dc2a45afb309594615213b37b918f9f9ccf4b69d76b7c4014ee8b9 |
|
creating new layer sha256:a2b99648f21d2974dcc96acd928740486d67dbd53b850aadd797dbfbfbd883d1 |
|
writing manifest |
|
success |
|
``` |
|
|
|
If it looks like that above, then run that shit! |
|
``` |
|
ollama run BlackSheep-Pi |
|
``` |
|
--- |
|
|
|
I will release the Base Model Soon Once I add a final Alignment Layer, currently adding some python skills to the model |
