Warning: mkdir(): No space left on device in /var/www/tg-me/post.php on line 37

Warning: file_put_contents(aCache/aDaily/post/machinelearning_interview/--): Failed to open stream: No such file or directory in /var/www/tg-me/post.php on line 50
Machine learning Interview | Telegram Webview: machinelearning_interview/1774 -
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 S&P 500 slumped 1.8% on Monday and Tuesday, thanks to China Evergrande, the Chinese property company that looks like it is ready to default on its more-than $300 billion in debt. Cries of the next Lehman Brothers—or maybe the next Silverado?—echoed through the canyons of Wall Street as investors prepared for the worst.

Machine learning Interview from ye


Telegram Machine learning Interview
FROM USA