Update README.md
This commit is contained in:
14
README.md
14
README.md
@@ -1,6 +1,6 @@
|
|||||||
# ucsinfer
|
# ucsinfer
|
||||||
|
|
||||||
Universal Category System inference.
|
Universal Category System LLM toolkit.
|
||||||
|
|
||||||
## Running
|
## Running
|
||||||
|
|
||||||
@@ -13,19 +13,21 @@ The subcommands available at this time are `gather` and `evaluate`.
|
|||||||
|
|
||||||
## Functions
|
## Functions
|
||||||
|
|
||||||
* recommend
|
* ~recommend~ (in-progress)
|
||||||
|
|
||||||
Infer a UCS category for a text description.
|
Infer a UCS category for a text description.
|
||||||
|
|
||||||
* gather
|
* gather
|
||||||
|
|
||||||
Scan files to capture existing text descriptions and UCS categories and save
|
Scan files to capture existing text descriptions and UCS categories
|
||||||
as a dataset.
|
and save as a dataset. This function is used to countruct datasets
|
||||||
|
that `evaluate` can use to test models and finetune can use to
|
||||||
|
refine them.
|
||||||
|
|
||||||
* finetune
|
* ~finetune~ (planned)
|
||||||
|
|
||||||
Fine-tune an existing sentence embedding model with training data.
|
Fine-tune an existing sentence embedding model with training data.
|
||||||
|
|
||||||
* evaluate
|
* evaluate
|
||||||
|
|
||||||
Use datasets to evauluate the performance of fine-tuning.
|
Use datasets to evaluate the performance of a model and fine-tuning.
|
||||||
|
Reference in New Issue
Block a user