Lewis Tunstall PRO
lewtun
AI & ML interests
LLMs, LLMs, LLMs
Recent Activity
liked
a Space
1 day ago
victor/pokedex
updated
a Space
3 days ago
open-r1/open-r1-eval-leaderboard
updated
a Space
3 days ago
open-r1/open-r1-eval-leaderboard
Organizations
lewtun's activity
[Experiment] Training R1-Zero-like models with Open R1
5
13
#20 opened 24 days ago
by
lewtun

about <think> and </think>
2
#9 opened about 1 month ago
by
volcanos

Please add HF Inference Endpoint and library tags which allow easier deployment
1
#8 opened about 1 month ago
by
SolshineMisfit

Mode changed to Model
2
#7 opened about 1 month ago
by
Solshine

Update README.md
1
#6 opened about 1 month ago
by
nickname100231
Omitted <think> at the start and almost 10k tokens to debug 2 JS functions
2
3
#2 opened about 1 month ago
by
operationdarkside
It seems to overthink
1
#3 opened about 1 month ago
by
sm54
Upload dataset
#4 opened about 1 month ago
by
lewtun

missing </think> in all subset
2
#3 opened about 1 month ago
by
volcanos

Why is there a discrepancy between the 'Solutions' subset and the 'Solutions_py' subset?
1
#2 opened about 1 month ago
by
waple

Update README.md
1
#1 opened about 1 month ago
by
lhoestq

Size of the weights > 140 GB for a 32 GB model?
1
1
#2 opened about 1 month ago
by
stelterlab

Remove fp32 weights
#4 opened about 1 month ago
by
lewtun

Remove fp32 weights
#3 opened about 1 month ago
by
lewtun

⚠️ Chat template foot gun with DeepSeek distilled models and RL format reward function
6
6
#17 opened 2 months ago
by
lewtun

the finetune config of open-r1?
2
#6 opened 2 months ago
by
MilyFang
Update README.md
3
#1 opened 2 months ago
by
davidberenstein1957

[Experiment] Applying GRPO to DeepSeek-R1-Distill-Qwen-1.5B with LIMO
22
22
#15 opened 2 months ago
by
lewtun

System Prompt
6
3
#3 opened 3 months ago
by
Wanfq

Is there a way to print this article?
1
2
#9 opened 4 months ago
by
iamgianluca