Alberto Ferrer

BarraHome's activity

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

liked a dataset 2 days ago

unsloth/jobs

Updated Feb 11 • 358 • 49

liked 3 datasets 10 days ago

nvidia/Nemotron-ClimbMix

Viewer • Updated Oct 21, 2025 • 355M • 12.1k • 88

karpathy/tinystories-gpt4-clean

Viewer • Updated Feb 8 • 2.73M • 2.99k • 61

openai/ih-challenge

Viewer • Updated Jan 12 • 27.6k • 215 • 11

upvoted a collection 18 days ago

Qwen3.5

Collection

21 items • Updated 11 days ago • 1.25k

liked 4 models about 1 month ago

LiquidAI/LFM2.5-1.2B-Thinking

Text Generation • 1B • Updated Feb 2 • 32.5k • 314

LiquidAI/LFM2.5-1.2B-Instruct

Text Generation • 1B • Updated 24 days ago • 232k • 533

concavity-ai/superlinear-exp-v0.1

Text Generation • 32B • Updated Feb 6 • 210 • 22

stepfun-ai/Step-3.5-Flash

Text Generation • 199B • Updated 4 days ago • 86.8k • • 728

liked 3 models about 2 months ago

meituan-longcat/LongCat-Flash-Lite

Text Generation • Updated Feb 6 • 1.04k • 178

codelion/malm-165m

Text Generation • Updated Jan 23 • 26 • 4

zai-org/GLM-4.7-Flash

Text Generation • 31B • Updated Jan 29 • 1.74M • • 1.62k

repliedto marksverdhei's post 2 months ago

view reply

Good call actually!

reactedto marksverdhei's post with 🔥 2 months ago

view post

Post

345

Hey if you're reading this and happen to be one of the guys training frontier llms, please penalize 404 urls in your reward functions. Happens too often that these models memorize / make up non-existing url paths and get away with it

See translation

• 
• 1 reply

·

🔥

1

1

+

Reply

repliedto mlabonne's post 2 months ago

view reply

32k? or 128k?

updated a model 3 months ago

BarraHome/Mistral-Small-24B-Instruct-EAGLE3-Speculator

0.8B • Updated Dec 24, 2025 • 7

published a model 3 months ago

BarraHome/Mistral-Small-24B-Instruct-EAGLE3-Speculator

0.8B • Updated Dec 24, 2025 • 7

liked 3 models 3 months ago

Tongyi-Zhiwen/QwenLong-L1.5-30B-A3B

Text Generation • 31B • Updated Jan 9 • 343 • 165

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Text Generation • 32B • Updated 6 days ago • 929k • 679

RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8-dynamic

Text Generation • 8B • Updated 1 day ago • 25.6k • 9