dame rajee's picture

dame rajee

damerajee

·

AI & ML interests

None yet

Recent Activity

reacted to lewtun's post with 🔥 about 21 hours ago

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! 🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. 🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code. 🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1

reacted to lewtun's post with 🤗 about 21 hours ago

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! 🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. 🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code. 🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1

reacted to lewtun's post with 🚀 about 21 hours ago

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! 🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. 🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code. 🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1

View all activity

Organizations

damerajee's activity

commented 2 papers 14 days ago

$\text{Transformer}^2$: Self-adaptive LLMs

Paper • 2501.06252 • Published 19 days ago • 51 •

$\text{Transformer}^2$: Self-adaptive LLMs

Paper • 2501.06252 • Published 19 days ago • 51 •

New activity in cointegrated/SONAR_200_text_encoder about 1 month ago

can you please do the same for decoder

#2 opened about 1 month ago by

New activity in argilla/FinePersonas-v0.1 4 months ago

How to make those beautiful banners on the readme?

#3 opened 4 months ago by

New activity in sarvamai/sarvam-2b-v0.5 5 months ago

Can we perform CPT?

#6 opened 5 months ago by

New activity in Kukedlc/Phi-3-Vision-Win-snap 8 months ago

Fine-tuning notebook or script?

#1 opened 8 months ago by

New activity in theblackcat102/llava-instruct-mix 8 months ago

How was this datasets made ?

#1 opened 9 months ago by

New activity in microsoft/Phi-3-vision-128k-instruct 8 months ago

Fine-tuning Phi-3-vision on custom dataset fails

#21 opened 8 months ago by

New activity in lamm-mit/Cephalo-Phi-3-vision-128k-4b-alpha 8 months ago

Could you provide finetuning script?

#1 opened 8 months ago by

New activity in google/paligemma-3b-mix-224 9 months ago

Does the processor contain apply_chat_template??

#4 opened 9 months ago by

New activity in RekaAI/VibeEval 9 months ago

How are these dataset made ?

#3 opened 9 months ago by

New activity in HuggingFaceH4/llava-instruct-mix-vsft 9 months ago

How are the images saved in this dataset?

#1 opened 9 months ago by

Update README.md

#2 opened 9 months ago by

New activity in damerajee/pretrained_large.v2 9 months ago

Librarian Bot: Add language metadata for dataset

#2 opened 9 months ago by

New activity in toshi456/llava-jp-1.3b-v1.1-pretrain 9 months ago

How long did it take you to pre-train and how much compute did it cost ?

#1 opened 9 months ago by

New activity in vikhyatk/lnqa 9 months ago

dataset format a bit weird

#4 opened 9 months ago by

New activity in Lin-Chen/ShareGPT4V 9 months ago

How to prepare the images?

#4 opened about 1 year ago by

New activity in damerajee/pretrained_large 10 months ago

Librarian Bot: Add language metadata for dataset

#1 opened 10 months ago by

New activity in visheratin/MC-LLaVA-3b 10 months ago

Pre training code

#9 opened 10 months ago by

New activity in Crystalcareai/GemMoE-Base-Random 10 months ago

Help

#4 opened 10 months ago by