Nicky

NickyNicky's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset about 20 hours ago

Nitral-AI/toxic-qa-style

Viewer • Updated about 22 hours ago • 6.85k • 29 • 1

liked 2 datasets about 21 hours ago

AymanTarig/xlam-function-calling-60k-llama-format

Viewer • Updated about 20 hours ago • 60k • 1

MinervaAI/Aesir-Preview

Viewer • Updated Feb 19, 2024 • 1k • 63 • 44

liked a dataset 1 day ago

Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B

Viewer • Updated 13 days ago • 250k • 2.26k • 58

reacted to nicolay-r's post with 👍 1 day ago

view post

Post

1994

🚨 Key takeaway of a quick mastering Sentiment Analysis nowadays. Trough the questionare 📝 of the past RuOpinoinNE-2024 competition we got insights and participants model preference chocies. Our main conclusion:

✨ The submissions of the top performed models exploit Few-shot learning for LLM.

Takeaway note comparing with the prior RuSentNE-2023 competition:
🧠 Reasoning in steps requires more actions for tweaking. Most recent solutions empowered with Chain-of-Thouhgt are tend to think too much. Earlier we might see improvements for the Flan-T5 (2.8B) in fine-tuned mode but not among the zero-shot approaches.
nicolay-r/flan-t5-tsa-thor-xl

Related materials:
https://github.com/dialogue-evaluation/RuOpinionNE-2024
RuSentNE-2023: Evaluating Entity-Oriented Sentiment Analysis on Russian News Texts (2305.17679)
Large Language Models in Targeted Sentiment Analysis (2404.12342)

See translation

• 

🧠

4

4

👍

2

2

+

Reply

liked a Space 2 days ago

Running on Zero

107

107

Chat With Dolphin

🐬

Chat with Cognitive Computation models 🐬

upvoted an article 2 days ago

view article

Article

wHy DoNt YoU jUsT uSe ThE lLaMa ToKeNiZeR??

By •

Sep 27, 2024

• 40

liked a dataset 2 days ago

dsrselfcorr/rl_prompt

Viewer • Updated 2 days ago • 416k • 8 • 1

liked 3 models 2 days ago

cognitivecomputations/Dolphin3.0-Mistral-24B

Text Generation • Updated 2 days ago • 2.29k • 29

cognitivecomputations/Dolphin3.0-R1-Mistral-24B

Text Generation • Updated 1 day ago • 625 • 75

nicolay-r/flan-t5-tsa-thor-xl

Text2Text Generation • Updated 11 days ago • 111 • 2

upvoted a paper 2 days ago

RuSentNE-2023: Evaluating Entity-Oriented Sentiment Analysis on Russian News Texts

Paper • 2305.17679 • Published May 28, 2023 • 2

liked a dataset 2 days ago

facebook/Self-taught-evaluator-DPO-data

Viewer • Updated 2 days ago • 57.5k • 57 • 32

liked a dataset 3 days ago

m-ric/Open_Assistant_Conversation_Chains

Viewer • Updated Nov 22, 2023 • 46.3k • 99 • 5

liked a model 3 days ago

kyutai/hibiki-1b-pytorch-bf16

Translation • Updated 3 days ago • 803 • 14

upvoted an article 3 days ago

view article

Article

Open-source DeepResearch – Freeing our search agents

5 days ago

• 797

liked 4 datasets 3 days ago

TIGER-Lab/WebInstruct-CFT

Viewer • Updated 7 days ago • 654k • 436 • 37

lightblue/reasoning-multilingual-R1-Llama-70B-train-nonunique

Viewer • Updated 9 days ago • 35k • 28 • 2

Kukedlc/Spanish_o1_CoT_8k

Viewer • Updated Dec 29, 2024 • 8.5k • 64 • 1

Kukedlc/spanish-train

Viewer • Updated May 19, 2024 • 958k • 92 • 1