Lewis Tunstall PRO

lewtun's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Qwen/Qwen3-4B-Instruct-2507 4 days ago

Sampling parameters to tau2-bench?

#8 opened 4 days ago by

lewtun

New activity in Qwen/Qwen3-4B-Thinking-2507 4 days ago

Sampling parameters & vLLM settings for tau2-bench?

#4 opened 4 days ago by

lewtun

New activity in HuggingFaceH4/Multilingual-Thinking 14 days ago

Update README.md

#2 opened 18 days ago by

reactkick

New activity in HuggingFaceTB/SmolLM3-3B about 1 month ago

Evaluation metrics

5

#20 opened about 1 month ago by

BounharAbdelaziz

Spelling mistake on model card

🤯 1

1

#24 opened about 1 month ago by

MihaiPopa-1

New activity in yhavinga/mc4_nl_cleaned about 1 month ago

Replace dataset script with data files

#2 opened about 1 month ago by

lewtun

New activity in a-m-team/AM-DeepSeek-R1-0528-Distilled 3 months ago

Unable to load dataset

1

#3 opened 3 months ago by

lewtun

New activity in open-thoughts/OpenThoughts3-1.2M 3 months ago

Closing </think> tag missing in 743814 (62%) of samples?

👍 12

3

#3 opened 3 months ago by

lewtun

Inconsistent eval scores between dataset card and blog post

3

#2 opened 3 months ago by

lewtun

New activity in open-r1/Mixture-of-Thoughts 3 months ago

Upload HTML.zip

#2 opened 3 months ago by

NOUREDDINE25

New activity in open-r1/OpenR1-Qwen-7B 3 months ago

Update evals with proper pass@1 scores

#8 opened 3 months ago by

lewtun

New activity in glaiveai/reasoning-v1-20m 4 months ago

Add domain categories?

2

#6 opened 4 months ago by

lewtun

New activity in open-r1/README 4 months ago

[Experiment] Training R1-Zero-like models with Open R1

👀 🔥 11

15

#20 opened 5 months ago by

lewtun

New activity in open-r1/OlympicCoder-32B 5 months ago

about <think> and </think>

2

#9 opened 5 months ago by

volcanos

Please add HF Inference Endpoint and library tags which allow easier deployment

1

#8 opened 5 months ago by

SolshineMisfit

Mode changed to Model

2

#7 opened 5 months ago by

Solshine

Update README.md

1

#6 opened 5 months ago by

nickname100231

New activity in open-r1/OlympicCoder-7B 5 months ago

Omitted <think> at the start and almost 10k tokens to debug 2 JS functions

➕ 2

3

#2 opened 5 months ago by

operationdarkside

It seems to overthink

1

#3 opened 5 months ago by

sm54

New activity in open-r1/codeforces-cots 5 months ago

Upload dataset

#4 opened 5 months ago by

lewtun