Need help, found a bug, or want a custom domain fine-tuned? Contact Abyssal-LLM@proton.me
-
intent-classifier-general-overall
The balanced pick: high accuracy and steady refusal together. Define intents at prompt time, no retraining. It returns the single best-matching name, or none_of_the_above when nothing fits. Rejects 74% of out-of-scope.
1.5b399 Pulls 1 Tag Updated 3 weeks ago
-
intent-classifier-general-acv3
The most accurate model in the family, and the best at telling lookalike intents apart. Define intents at prompt time, no retraining. It always returns the single best match, and refuses only if you add a catch-all intent.
1.5b395 Pulls 1 Tag Updated 4 days ago
-
intent-classifier-general-v3
More accurate than v2, and lighter on refusal. Define intents at prompt time, no retraining. It returns the single best-matching name, or none_of_the_above when nothing fits, refusing 67% of out-of-scope messages.
1.5b274 Pulls 1 Tag Updated 3 weeks ago
-
intent-classifier-general-v2
The first in the family that can decline. Define intents at prompt time, no retraining. It returns the single best-matching name, or none_of_the_above when nothing fits, refusing 84% of out-of-scope messages.
1.5b246 Pulls 1 Tag Updated 3 weeks ago
-
intent-classifier-general-oav2
The strictest gatekeeper here, rejecting 87% of out-of-scope messages - the highest in the family. Define intents at prompt time, no retraining. It returns the best-matching name, or none_of_the_above when nothing fits.
1.5b240 Pulls 1 Tag Updated 1 week ago
-
intent-classifier-general
The original in the family. A tiny, promptable intent classifier: define your intents in the prompt, no retraining, and it returns the single best-matching name. It always picks one - there is no refusal option.
1.5b205 Pulls 1 Tag Updated 1 month ago
-
intent-classifier-general-acv1
Accuracy first, with refusal still built in. Define intents at prompt time, no retraining. It returns the single best-matching name, or none_of_the_above when nothing fits. Pick it when you want both at once.
1.5b182 Pulls 1 Tag Updated 1 week ago
-
intent-classifier-general-accuracy
Never refuses: it always returns the single best-matching intent, defined at prompt time with no retraining. Refusal is opt-in via a catch-all intent, which it grabs less eagerly than acv3. For higher accuracy, see acv3.
1.5b164 Pulls 1 Tag Updated 6 days ago