Krishna Kaasyap

KrishnaKaasyap

AI & ML interests

Test Time Training Multimodal & Inter-Modality Transfer Learning Mechanistic Interpretability Evolutionary Model Merging Swarm Intelligence of multiple models with different architectures and different algorithms MuZero approach to general tasks

Recent Activity

upvoted a collection about 18 hours ago

Llama 4

liked a model 11 days ago

Qwen/Qwen2.5-Omni-7B

liked a model 22 days ago

CohereForAI/c4ai-command-a-03-2025

View all activity

Organizations

KrishnaKaasyap's activity

New activity in RekaAI/reka-flash-3 26 days ago

Context length and reasoning length?

#6 opened 26 days ago by

KrishnaKaasyap

New activity in unsloth/DeepSeek-R1-BF16 2 months ago

Any performance improvements??

#2 opened 2 months ago by

KrishnaKaasyap

New activity in deepseek-ai/DeepSeek-R1-Distill-Llama-70B 3 months ago

SFT (Non-RL) distillation is this good on a sub-100B model?

#2 opened 3 months ago by

KrishnaKaasyap

New activity in deepseek-ai/DeepSeek-R1 3 months ago

Is this the same as DeepSeek-R1 (Preview) mentioned on LiveCodeBench?

#10 opened 3 months ago by

KrishnaKaasyap

New activity in deepseek-ai/DeepSeek-R1-Zero 3 months ago

Hail CCP!!! God bless Chyna!

#3 opened 3 months ago by

mnemojeet

Thank you deepseek

#8 opened 3 months ago by

teknium

New activity in deepseek-ai/DeepSeek-V3 3 months ago

How can we thank you enough, whale bros?

#1 opened 3 months ago by

KrishnaKaasyap

commented a paper 12 months ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22, 2024 • 258 •

commented a paper about 1 year ago

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

Paper • 2402.19427 • Published Feb 29, 2024 • 56 •

New activity in 01-ai/Yi-34B-200K over 1 year ago

Wow, the sky is the limit!

#1 opened over 1 year ago by

KrishnaKaasyap

New activity in togethercomputer/RedPajama-Data-V2 over 1 year ago

Open source community will forever be indebted to Together AI.

#1 opened over 1 year ago by

KrishnaKaasyap

New activity in SciPhi/SciPhi-Mistral-7B-32k over 1 year ago

Just tested with some legal text - and here's my opinion/human eval.

#1 opened over 1 year ago by

KrishnaKaasyap

New activity in HuggingFaceH4/zephyr-7b-alpha over 1 year ago

APIs & Fine-tuning ( both Domain Adaptation and instruction fine-tuning) on $/1000 token basis

#12 opened over 1 year ago by

KrishnaKaasyap

commented a paper over 1 year ago

Table-GPT: Table-tuned GPT for Diverse Table Tasks

Paper • 2310.09263 • Published Oct 13, 2023 • 41 •

New activity in teknium/Phi-Hermes-1.3B over 1 year ago

Inference speed on A

#4 opened over 1 year ago by

KrishnaKaasyap

New activity in microsoft/phi-1_5 over 1 year ago

Inference time is much longer than reported

#25 opened over 1 year ago by

jeff-gao

Question answering format

#49 opened over 1 year ago by

codegood