Edd's picture

Edd

Erland

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 6 days ago

upvoted an article 8 days ago

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

upvoted an article 8 days ago

Continuous batching from first principles

View all activity

Organizations

None yet

Erland 's models 186

Erland/vanillaFT-gsm8k-math-1.8B-4096-model-5epochs

2B • Updated 20 days ago • 52

Erland/vanillaFT-gsm8k-math-1.8B-4096-model

2B • Updated 21 days ago • 30

Erland/GemmaFT-gsm8k-math-270M-4096-model

Text Generation • 0.3B • Updated 24 days ago • 35

Erland/vanillaFT-gsm8k-1.8B-4096-model

2B • Updated 24 days ago • 27

Erland/vanillaFT-gsm8k-340M-4096-model

0.4B • Updated 24 days ago • 59

Erland/softpick-120M-4096-model

0.1B • Updated 26 days ago • 31

Erland/sst0.9-120M-4096-model

0.1B • Updated 26 days ago • 25

Erland/sst0.7-120M-4096-model

0.1B • Updated 27 days ago • 18

Erland/gemma-3-finetune

0.3B • Updated 28 days ago • 57

Erland/sst0.3-120M-4096-model

0.1B • Updated 28 days ago • 24

Erland/vanilla-120M-4096-model

0.1B • Updated 28 days ago • 42

Erland/LlaMA-3.2-1B-Instruct

Text Generation • 1B • Updated Nov 3 • 67

Erland/gemma-3-270m-it

Text Generation • 0.3B • Updated Sep 10 • 6

Erland/MTP-120M

0.1B • Updated Jun 13 • 9

Erland/mtp-120M-4096-batch16-steps100000-20250613-111312

Erland/mtp-120M-4096-batch16-steps100000-20250613-110851

Erland/mtp-120M-4096-batch16-steps100000-20250613-110542

Erland/mtp-120M-4096-batch16-steps100000-20250613-105826

Erland/Qwen3Softpick-8B-Base

Text Generation • 8B • Updated Jun 4 • 5

Erland/gpt2-tokenizer

Erland/DeepSeek-R1-0528-Qwen3-8B

Text Generation • 8B • Updated May 29 • 7

Erland/vanilla-1.8B-4096-model-HQQ-3bit

Text Generation • Updated May 29 • 10

Erland/vanilla-1.8B-4096-model-HQQ-2bit

Text Generation • Updated May 29 • 7

Erland/softpick-1.8B-4096-model-HQQ-3bit

Text Generation • Updated May 29 • 9

Erland/softpick-1.8B-4096-model-HQQ-2bit

Text Generation • Updated May 29 • 12

Erland/vanilla-340M-4096-model-HQQ-3bit

Text Generation • Updated May 29 • 6

Erland/Qwen2-0.5B-SFT-lora-default

Erland/softpick-1.8B-4096-model-GPTQ-2bit

Text Generation • 0.2B • Updated May 27 • 5

Erland/softpick-1.8B-4096-model-GPTQ-4bit

Text Generation • 0.4B • Updated May 27 • 6

Erland/softpick-1.8B-4096-model-GPTQ-3bit

Text Generation • 0.3B • Updated May 27 • 6