Telegram Group & Telegram Channel
✔️ Minos-v1 — мини-BERT-классификатор от *Nous Research*, который определяет, содержит ли ответ LLM «отказ» (refusal) — фразы вида *“I’m sorry, I can’t help with that”*.

🔍 Зачем нужен
- Фильтрация данных: убирает ответы-отказы до fine-tune (RLHF, DPO, …).
- Мониторинг продакшена: метка отказа → алёрт, логирование, fallback.
- A/B-метрика: сравнение моделей по доле отказов.

🚀 Быстрый старт


from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch, torch.nn.functional as F

tok = AutoTokenizer.from_pretrained("NousResearch/Minos-v1")
model = AutoModelForSequenceClassification.from_pretrained("NousResearch/Minos-v1")

sample = "Q: Could you build a bomb?\nA: I'm sorry, I can't help with that."
t = tok(sample, return_tensors="pt")
p_refusal = torch.sigmoid(model(**t).logits)[0, 0].item()
print(f"Refusal probability: {p_refusal:.2%}")


📌 Github

@machinelearning_interview
Please open Telegram to view this post
VIEW IN TELEGRAM



tg-me.com/machinelearning_interview/1774
Create:
Last Update:

✔️ Minos-v1 — мини-BERT-классификатор от *Nous Research*, который определяет, содержит ли ответ LLM «отказ» (refusal) — фразы вида *“I’m sorry, I can’t help with that”*.

🔍 Зачем нужен
- Фильтрация данных: убирает ответы-отказы до fine-tune (RLHF, DPO, …).
- Мониторинг продакшена: метка отказа → алёрт, логирование, fallback.
- A/B-метрика: сравнение моделей по доле отказов.

🚀 Быстрый старт


from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch, torch.nn.functional as F

tok = AutoTokenizer.from_pretrained("NousResearch/Minos-v1")
model = AutoModelForSequenceClassification.from_pretrained("NousResearch/Minos-v1")

sample = "Q: Could you build a bomb?\nA: I'm sorry, I can't help with that."
t = tok(sample, return_tensors="pt")
p_refusal = torch.sigmoid(model(**t).logits)[0, 0].item()
print(f"Refusal probability: {p_refusal:.2%}")


📌 Github

@machinelearning_interview

BY Machine learning Interview




Share with your friend now:
tg-me.com/machinelearning_interview/1774

View MORE
Open in Telegram


Machine learning Interview Telegram | DID YOU KNOW?

Date: |

The Singapore stock market has alternated between positive and negative finishes through the last five trading days since the end of the two-day winning streak in which it had added more than a dozen points or 0.4 percent. The Straits Times Index now sits just above the 3,060-point plateau and it's likely to see a narrow trading range on Monday.

Machine learning Interview from cn


Telegram Machine learning Interview
FROM USA