|
--- |
|
license: mit |
|
--- |
|
|
|
Fine-tune of https://huggingface.co/suayptalha/Falcon3-Jessi-v0.4-7B-Slerp using a custom training script, custom loss function, custom optimizer. |
|
|
|
This is a first try at creating a small reasoning model that uses its own symbolic language to represent different reasoning steps. |
|
|
|
Very weird, experimental, frequently broken model which occasionally does something cool and/or surprising. |
|
|
|
Trained on a single 3090 targeting only `q_proj` and `gate_proj` on blocks 7,8,9,25,26,27 |
|
|
|
This is the syntax for the DSL I trained it on, which is called ROL (Reasoning Operations Language). |
|
``` |
|
## Core Symbols |
|
`˩` (low), `˧` (medium), `˥` (extreme). |
|
`⟡` Generate - Propose solutions/alternatives. |
|
`⚖` Evaluate - Weigh options against logic/emotion. |
|
`☮` Empathize - Model user’s emotional state. |
|
`⧟` Integrate - Synthesize memories, knowledge. |
|
`⌬` Knowledge - Factual recall with confidence. |
|
`֍` Thought - A sentence expressing private personal opinions about the query. |
|
`☠` Threat - Identify risks/uncertainty. |
|
`✔` Resolve - Commit to actions post-conflict. |
|
`↺` Self-Reflect - Reconsider assumptions, mitigate overconfidence. Usually begins with the word "Wait" or "Alternatively" or "Actually". Use this at least 3 times. |
|
`➤` Output - Structure tone, format, intent. |
|
``` |
|
ROL was invented by Deepseek R1 and tweaked by me. The spec for it was not included in the training data - the model figured out how it works based on a synthetic hand-edited dataset with 65 samples. |
|
|
|
The total training time for this was under 15 minutes. |
|
|
|
|
|
 |
|
|
