garrett galloway's picture

garrett galloway PRO

RecViking

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago
Qwen/Qwen3-32B
liked a model about 1 month ago
microsoft/Phi-4-reasoning-plus
new activity 3 months ago
microsoft/phi-4:Phi-4 with Tools
View all activity

Organizations

Hugging Face Discord Community's profile picture

RecViking's activity

New activity in microsoft/phi-4 3 months ago

Phi-4 with Tools

4
#28 opened 5 months ago by
tahafatih
reacted to lewtun's post with ๐Ÿ”ฅ 4 months ago
view post
Post
10398
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!

๐Ÿงช Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.

๐Ÿง  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.

๐Ÿ”ฅ Step 3: show we can go from base model -> SFT -> RL via multi-stage training.

Follow along: https://github.com/huggingface/open-r1
ยท
New activity in OpenAssistant/falcon-40b-sft-top1-560 almost 2 years ago
New activity in HuggingFaceH4/starchat-alpha about 2 years ago

CPU bound when loaded on GPU?

2
#6 opened about 2 years ago by
RecViking
New activity in HuggingFaceH4/starchat-alpha about 2 years ago