Deepseek Papers
Collection
Deepseek papers collection
•
15 items
•
Updated
•
46
poterliu
poterliu
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
7 days ago
Deepseek Papers
liked
a Space
8 days ago
Qwen/Qwen2.5-Max-Demo
liked
a Space
10 days ago
akhaliq/anychat
Organizations
None yet
poterliu's activity
upvoted
a
collection
7 days ago
liked
a
Space
8 days ago
liked
a
Space
10 days ago
upvoted
a
collection
10 days ago
liked
2
models
10 days ago
upvoted
a
collection
11 days ago
reacted to
lewtun's
post with 🤗
11 days ago
Post
9886
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
🧪 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
- 5 replies
liked
a
model
11 days ago
reacted to
onekq's
post with 👍
11 days ago
Post
2271
So 🐋DeepSeek🐋 hits the mainstream media. But it has been a star in our little cult for at least 6 months. Its meteoric success is not overnight, but two years in the making.
To learn their history, just look at their 🤗 repo https://huggingface.co/deepseek-ai
* End of 2023, they launched the first model (pretrained by themselves) following Llama 2 architecture
* June 2024, v2 (MoE architecture) surpassed Gemini 1.5, but behind Mistral
* September, v2.5 surpassed GPT 4o mini
* December, v3 surpassed GPT 4o
* Now R1 surpassed o1
Most importantly, if you think DeepSeek success is singular and unrivaled, that's WRONG. The following models are also near or equal the o1 bar.
* Minimax-01
* Kimi k1.5
* Doubao 1.5 pro
To learn their history, just look at their 🤗 repo https://huggingface.co/deepseek-ai
* End of 2023, they launched the first model (pretrained by themselves) following Llama 2 architecture
* June 2024, v2 (MoE architecture) surpassed Gemini 1.5, but behind Mistral
* September, v2.5 surpassed GPT 4o mini
* December, v3 surpassed GPT 4o
* Now R1 surpassed o1
Most importantly, if you think DeepSeek success is singular and unrivaled, that's WRONG. The following models are also near or equal the o1 bar.
* Minimax-01
* Kimi k1.5
* Doubao 1.5 pro
- 1 reply
upvoted
a
paper
11 days ago
liked
a
Space
11 days ago
liked
a
dataset
11 days ago
liked
3
models
17 days ago
liked
2
models
22 days ago
upvoted
a
paper
22 days ago
liked
a
model
about 1 month ago
