126 11 687

Nicholas Beerbower PRO

nbeerbower

jmeosbn's profile picture

Delta-Vector's profile picture

zetasepic's profile picture

https://ko-fi.com/birubawa

nsbeerbower
nbeerbower

AI & ML interests

QLoRA finetuning and merging LLMs for fun

Recent Activity

liked a model 1 day ago

NovelAI/nai-anime-v2

liked a dataset 5 days ago

OmniGen2/X2I2

liked a model 5 days ago

OmniGen2/OmniGen2

View all activity

Organizations

nbeerbower 's collections 8

DPO

Various useful datasets with preference optimization

jondurbin/gutenberg-dpo-v0.1

Viewer • Updated Jan 12, 2024 • 918 • 714 • 147
nbeerbower/gutenberg2-dpo

Viewer • Updated Nov 16, 2024 • 293 • 73 • 20
jondurbin/truthy-dpo-v0.1

Viewer • Updated Jan 11, 2024 • 1.02k • 299 • 134
kyujinpy/orca_math_dpo

Viewer • Updated Apr 12, 2024 • 15.3k • 162 • 19

Dumplings

Qwen2.5 finetunes aiming for decensorship and improved english prose

nbeerbower/Dumpling-Qwen2.5-32B

Text Generation • 33B • Updated Jan 24 • 42 • 10
nbeerbower/Dumpling-Qwen2.5-14B

Text Generation • 15B • Updated Feb 14 • 5 • 4
nbeerbower/Dumpling-Qwen2.5-1.5B-v2

Text Generation • 2B • Updated Feb 4 • 10 • 2
nbeerbower/Dumpling-Qwen2.5-1.5B

Text Generation • 2B • Updated Feb 1 • 6 • 1

bruphin

Series of merge experiments attempting to make a small uncensored ChatML model based initially on ehartford/dolphin and rwitz/go-bruins-v2 mistral-7B

nbeerbower/bruphin-lambda

Text Generation • 7B • Updated Apr 3, 2024 • 9
nbeerbower/bruphin-kappa

Text Generation • 7B • Updated Mar 24, 2024 • 6 • 1
nbeerbower/bruphin-iota

Text Generation • 7B • Updated Mar 24, 2024 • 30 • 1
nbeerbower/bruphin-theta

Text Generation • 7B • Updated Mar 10, 2024 • 7

llama 3 experiments

Merge and finetune experiments with llama 3, aiming for decensorship and benchmark performance.

nbeerbower/llama-3-stella-truthy-dpo-8B

Text Generation • 8B • Updated May 6, 2024 • 17 • 1
nbeerbower/llama-3-stella-8B

Text Generation • 8B • Updated May 6, 2024 • 21 • 2
nbeerbower/llama-3-bible-dpo-8B

Text Generation • 8B • Updated May 6, 2024 • 24 • 3
nbeerbower/llama-3-wissenschaft-8B-v2

Text Generation • 8B • Updated May 5, 2024 • 49 • 1

Qwen3

my qwen3 tunes

nbeerbower/Yanfei-v2-Qwen3-32B

Text Generation • 33B • Updated 29 days ago • 87 • 1
nbeerbower/Vitus-Qwen3-14B

15B • Updated about 1 month ago • 56 • 3
nbeerbower/Xiaolong-Qwen3-14B

Text Generation • 15B • Updated May 9 • 62 • 9
nbeerbower/Xiaolong-Qwen3-8B

Text Generation • 8B • Updated May 8 • 27 • 4

abliteration loras

Extracted adapters for removing censorship in models

nbeerbower/Qwen2.5-32B-abliterated-LORA

Updated Apr 28 • 2
nbeerbower/Mistral-Nemo-12B-abliterated-LORA

Updated Oct 19, 2024 • 3
mlabonne/Llama-3-70B-Instruct-abliterated-LORA

Updated Aug 4, 2024 • 7

flammen

Merge & finetune experiments aiming for strong character roleplay, creative writing, and overall good performance.

flammenai/flammen32-mistral-7B

Text Generation • 7B • Updated Jun 1, 2024 • 10 • 1
flammenai/flammen31-mistral-7B

Text Generation • 7B • Updated Jun 1, 2024 • 18 • 2
flammenai/flammen30-mistral-7B

Text Generation • 7B • Updated May 29, 2024 • 10 • 1
flammenai/flammen29-mistral-7B

Text Generation • 7B • Updated May 27, 2024 • 8 • 1

Nemo

Mistral Nemo 12B finetunes and merges

nbeerbower/mistral-nemo-bophades-12B

Text Generation • 12B • Updated Sep 6, 2024 • 75 • • 9
nbeerbower/Lyra-Gutenberg-mistral-nemo-12B

Text Generation • 12B • Updated Sep 13, 2024 • 76 • • 19
nbeerbower/mistral-nemo-gutenberg-12B-v4

Text Generation • 12B • Updated Sep 6, 2024 • 75 • • 21
nbeerbower/mistral-nemo-gutenberg-12B-v3

Text Generation • 12B • Updated Sep 4, 2024 • 27 • 11

DPO

Various useful datasets with preference optimization

jondurbin/gutenberg-dpo-v0.1

Viewer • Updated Jan 12, 2024 • 918 • 714 • 147
nbeerbower/gutenberg2-dpo

Viewer • Updated Nov 16, 2024 • 293 • 73 • 20
jondurbin/truthy-dpo-v0.1

Viewer • Updated Jan 11, 2024 • 1.02k • 299 • 134
kyujinpy/orca_math_dpo

Viewer • Updated Apr 12, 2024 • 15.3k • 162 • 19

Qwen3

my qwen3 tunes

nbeerbower/Yanfei-v2-Qwen3-32B

Text Generation • 33B • Updated 29 days ago • 87 • 1
nbeerbower/Vitus-Qwen3-14B

15B • Updated about 1 month ago • 56 • 3
nbeerbower/Xiaolong-Qwen3-14B

Text Generation • 15B • Updated May 9 • 62 • 9
nbeerbower/Xiaolong-Qwen3-8B

Text Generation • 8B • Updated May 8 • 27 • 4

Dumplings

Qwen2.5 finetunes aiming for decensorship and improved english prose

nbeerbower/Dumpling-Qwen2.5-32B

Text Generation • 33B • Updated Jan 24 • 42 • 10
nbeerbower/Dumpling-Qwen2.5-14B

Text Generation • 15B • Updated Feb 14 • 5 • 4
nbeerbower/Dumpling-Qwen2.5-1.5B-v2

Text Generation • 2B • Updated Feb 4 • 10 • 2
nbeerbower/Dumpling-Qwen2.5-1.5B

Text Generation • 2B • Updated Feb 1 • 6 • 1

abliteration loras

Extracted adapters for removing censorship in models

nbeerbower/Qwen2.5-32B-abliterated-LORA

Updated Apr 28 • 2
nbeerbower/Mistral-Nemo-12B-abliterated-LORA

Updated Oct 19, 2024 • 3
mlabonne/Llama-3-70B-Instruct-abliterated-LORA

Updated Aug 4, 2024 • 7

bruphin

Series of merge experiments attempting to make a small uncensored ChatML model based initially on ehartford/dolphin and rwitz/go-bruins-v2 mistral-7B

nbeerbower/bruphin-lambda

Text Generation • 7B • Updated Apr 3, 2024 • 9
nbeerbower/bruphin-kappa

Text Generation • 7B • Updated Mar 24, 2024 • 6 • 1
nbeerbower/bruphin-iota

Text Generation • 7B • Updated Mar 24, 2024 • 30 • 1
nbeerbower/bruphin-theta

Text Generation • 7B • Updated Mar 10, 2024 • 7

flammen

Merge & finetune experiments aiming for strong character roleplay, creative writing, and overall good performance.

flammenai/flammen32-mistral-7B

Text Generation • 7B • Updated Jun 1, 2024 • 10 • 1
flammenai/flammen31-mistral-7B

Text Generation • 7B • Updated Jun 1, 2024 • 18 • 2
flammenai/flammen30-mistral-7B

Text Generation • 7B • Updated May 29, 2024 • 10 • 1
flammenai/flammen29-mistral-7B

Text Generation • 7B • Updated May 27, 2024 • 8 • 1

llama 3 experiments

Merge and finetune experiments with llama 3, aiming for decensorship and benchmark performance.

nbeerbower/llama-3-stella-truthy-dpo-8B

Text Generation • 8B • Updated May 6, 2024 • 17 • 1
nbeerbower/llama-3-stella-8B

Text Generation • 8B • Updated May 6, 2024 • 21 • 2
nbeerbower/llama-3-bible-dpo-8B

Text Generation • 8B • Updated May 6, 2024 • 24 • 3
nbeerbower/llama-3-wissenschaft-8B-v2

Text Generation • 8B • Updated May 5, 2024 • 49 • 1

Nemo

Mistral Nemo 12B finetunes and merges

nbeerbower/mistral-nemo-bophades-12B

Text Generation • 12B • Updated Sep 6, 2024 • 75 • • 9
nbeerbower/Lyra-Gutenberg-mistral-nemo-12B

Text Generation • 12B • Updated Sep 13, 2024 • 76 • • 19
nbeerbower/mistral-nemo-gutenberg-12B-v4

Text Generation • 12B • Updated Sep 6, 2024 • 75 • • 21
nbeerbower/mistral-nemo-gutenberg-12B-v3

Text Generation • 12B • Updated Sep 4, 2024 • 27 • 11