Offer L.'s picture

2 2 89

Offer L.

OfferL

·

AI & ML interests

None yet

Recent Activity

reacted to chansung's post with 👍 3 days ago

Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind) The process starts by posing a question. 1) The LLM generates initial responses. 2) These generated responses are evaluated according to specific criteria (program-based checker). 3) The LLM critiques the evaluated results. 4) The LLM refines the responses based on the evaluation, critique, and original responses. The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged). Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios. However, there are two major drawbacks: 🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.) 🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.) https://arxiv.org/abs/2501.09891

liked a model about 2 months ago

meta-llama/Llama-3.3-70B-Instruct

liked a Space about 2 months ago

ivrit-ai/hebrew-transcription-leaderboard

View all activity

Organizations

OfferL's activity

liked a model about 2 months ago

meta-llama/Llama-3.3-70B-Instruct

Text Generation • Updated Dec 21, 2024 • 586k • • 1.76k

liked a Space about 2 months ago

Hebrew Transcription Leaderboard

liked a model 3 months ago

mistralai/Mistral-Large-Instruct-2407

Updated Oct 16, 2024 • 1.54M • 819

liked a model 5 months ago

mattshumer/Reflection-Llama-3.1-70B

Text Generation • Updated Sep 24, 2024 • 654 • 1.71k

liked 5 Spaces 5 months ago

Qwen Math Demo

Running on Zero

Llama3.1 S V0.2 Checkpoint 2024 08 20

Running on CPU Upgrade

Kolors Virtual Try-On

Running on Zero

Falcon Mamba Playground

Paligemma HF

liked a Space 6 months ago

Running on Zero

FLUX.1 [dev]

liked a model 6 months ago

black-forest-labs/FLUX.1-dev

Text-to-Image • Updated Aug 16, 2024 • 1.49M • • 8.25k

liked 3 Spaces 6 months ago

Running on Zero

Mistral-lab

Chat with Mistral

Vidore Leaderboard

Running on Zero

ColPali

Document Retrieval

liked a model 6 months ago

vidore/colpali

Updated Sep 27, 2024 • 39k • 410

liked 2 Spaces 7 months ago

Running on Zero

Gemma 2 llama.cpp 2B/9B/27B

AI2 WildBench Leaderboard (V2)

liked 2 models 7 months ago

meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • Updated Sep 27, 2024 • 1.94M • • 3.78k

nvidia/Nemotron-4-340B-Instruct

Updated Jun 24, 2024 • 96 • 667

liked a Space 7 months ago

Running on Zero

OpenGPT 4o

GPT 4o like bot.