68 1 6

TeeZee

MarinaraSpaghetti's profile picture

iongun's profile picture

OxyLee's profile picture

AI & ML interests

LLM Roleplaying, on a quest to create a perfect model

Recent Activity

updated a model 9 days ago

TeeZee/Nemotron-9b-v2-abliterated

published a model 9 days ago

TeeZee/Nemotron-9b-v2-abliterated

new activity 22 days ago

DontPlanToEnd/UGI-Leaderboard:Eval request

View all activity

Organizations

None yet

TeeZee 's collections 13

Heretic models

What AI would look like if it was free from censorship

TeeZee/gemma-3-27b-it-heretic

Image-Text-to-Text • 27B • Updated 25 days ago • 24
TeeZee/gemma-3-27b-it-heretic-v2

Image-Text-to-Text • 27B • Updated 25 days ago • 25
TeeZee/gpt-oss-120b-heretic-v1

Text Generation • 117B • Updated 24 days ago • 21
TeeZee/Llama-3.3-70B-Instruct-heretic

Text Generation • 71B • Updated 24 days ago • 27

Kyllene

Model series for RPG/ERP

TeeZee/Kyllene-57B-v1.0

Text Generation • 57B • Updated Mar 4, 2024 • 21 • 7
TeeZee/Kyllene-34B-v1.1

Text Generation • 34B • Updated Jun 28, 2024 • 27 • 16
TeeZee/Kyllene-34B-v1.1-GGUF

34B • Updated Jun 28, 2024 • 531 • 4
TeeZee/Kyllene-57B-v1.0-GGUF

57B • Updated Jan 28, 2024 • 120 • 1

Buttocks

Totally unhinged models collection.

TeeZee/Buttocks-7B-v1.0

Text Generation • 7B • Updated Mar 4, 2024 • 57 • 4
TeeZee/Buttocks-7B-v1.1

Text Generation • 7B • Updated Mar 4, 2024 • 62 • 3

Writing style transfer experiments

LLMs with specific writing style

TeeZee/llama-2-7B-pirate-speech-60s

Text Generation • 7B • Updated May 26 • 7
TeeZee/llama-2-7B-pirate-speech-QLORA-60-steps

Text Generation • 4B • Updated Feb 16, 2024 • 5
TeeZee/llama-2-7B-pirate-speech-600s

Text Generation • 7B • Updated Jul 6 • 10
TeeZee/dolly-15k-pirate-speech

Viewer • Updated Feb 18, 2024 • 15k • 97 • 1

Workbench

Untested and unfinished models. Works in progress.

TeeZee/GALAXY-XB-v.01

Text Generation • 18B • Updated Mar 10, 2024 • 67
TeeZee/GALAXY-XB-v.02

Text Generation • 17B • Updated Mar 10, 2024 • 72
TeeZee/GALAXY-XB-v.03

Text Generation • 16B • Updated Mar 30, 2024 • 75
TeeZee/GALAXY_v03_slimorca_1_epoch_50k

Text Generation • 16B • Updated Mar 30, 2024 • 92

LASERS

Fun with LASERS (https://github.com/cognitivecomputations/laserRMT)

TeeZee/Phi-3-mini-4k-instruct-LASER

Text Generation • 4B • Updated May 9, 2024 • 14
TeeZee/Phi-3-mini-128k-instruct-LASER

Text Generation • 4B • Updated May 9, 2024 • 12

48 GB VRAM

Quants that run fast on 2x3090 consuming 48GB total VRAM.

TeeZee/Reflection-Llama-3.1-70B-GGUF

71B • Updated Sep 10, 2024 • 25 • 1
TeeZee/Reflection-Llama-3.1-70B-bpw4.0-h8-exl2

Updated Sep 9, 2024 • 5 • 2

24 GB VRAM

Quants that run fast on single 3090/4090 card with 24GB of VRAM and 4096 context length

TeeZee/2xbagel-dpo-34b-v0.2-bpw3.0-h6-exl2

Text Generation • Updated Jun 28, 2024 • 14 • 1
TeeZee/2xNous-Capybara-34B-bpw3-h6-exl2

Text Generation • Updated Jan 14, 2024 • 6
TeeZee/Psyfighter2-Orca2-13B-ties-bpw8.0-h8-exl2

Text Generation • Updated Jan 12, 2024 • 8
TeeZee/chronomaid-storytelling-13B-bpw8.0-h8-exl2

Text Generation • Updated Jan 13, 2024 • 6

Dark Forests

Models for mature, intriguing storytelling and RP/ERP.

TeeZee/DarkForest-20B-v1.0

Text Generation • 20B • Updated Jan 28, 2024 • 80 • 3
TeeZee/DarkForest-20B-v1.0-GGUF

20B • Updated Feb 18, 2024 • 119 • 3
TeeZee/DarkSapling-7B-v1.0

Text Generation • 7B • Updated Mar 4, 2024 • 61
TeeZee/DarkSapling-7B-v1.1

Text Generation • 7B • Updated Mar 4, 2024 • 61 • 1

12 GB VRAM

Quants that run fast on card with 12GB of VRAM and 4096 context length

TeeZee/DarkForest-20B-v2.0-bpw4.0-h6-exl2

Text Generation • Updated Feb 18, 2024 • 9 • 3
TeeZee/BigMaid_20B_v1.0-bpw3.0-h6-exl2

Text Generation • Updated Mar 2, 2024 • 10 • 2
TeeZee/DarkForest-20B-v2.0-bpw3.0-h6-exl2

Text Generation • Updated Mar 2, 2024 • 10 • 1
TeeZee/DarkForest-20B-v2.0-bpw3.5-h6-exl2

Text Generation • Updated Mar 9, 2024 • 9

15 GB Colab

Quants that run on 1xT4 on Colab

TeeZee/DarkForest-20B-v2.0-bpw4.5-h6-exl2

Text Generation • Updated Mar 7, 2024 • 11 • 1
TeeZee/DarkForest-20B-v2.0-bpw4.6-h6-exl2

Text Generation • Updated Mar 8, 2024 • 9
TeeZee/DarkForest-20B-v2.0-bpw4.55-h6-exl2

Text Generation • Updated Mar 9, 2024 • 8 • 1
TeeZee/BigMaid_20B_v1.0-bpw4.55-h6-exl2

Text Generation • Updated Mar 19, 2024 • 12 • 1

Polish speaking LLMs

LMMs that can coherently speak polish language.

TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1

Text Generation • 11B • Updated Apr 11, 2024 • 18
TeeZee/Qra-13b-instruct

Text Generation • 13B • Updated Aug 19, 2024 • 20
TeeZee/Qra-13B-chat

Text Generation • 13B • Updated Aug 28, 2024 • 16

BigMaid

Fun to talk to models.

TeeZee/BigMaid-20B-v1.0

Text Generation • 20B • Updated Mar 4, 2024 • 62 • 3
TeeZee/BigMaid-20B-v2.0

Text Generation • 20B • Updated Jun 15, 2024 • 10 • 3
TeeZee/BigMaid-20B-v2.0-bpw8.0-h8-exl2

Text Generation • Updated Jun 15, 2024 • 4
TeeZee/BigMaid-20B-v1.0-bpw8.0-h8-exl2

Text Generation • Updated Feb 9, 2024 • 10 • 1

Heretic models

What AI would look like if it was free from censorship

TeeZee/gemma-3-27b-it-heretic

Image-Text-to-Text • 27B • Updated 25 days ago • 24
TeeZee/gemma-3-27b-it-heretic-v2

Image-Text-to-Text • 27B • Updated 25 days ago • 25
TeeZee/gpt-oss-120b-heretic-v1

Text Generation • 117B • Updated 24 days ago • 21
TeeZee/Llama-3.3-70B-Instruct-heretic

Text Generation • 71B • Updated 24 days ago • 27

24 GB VRAM

Quants that run fast on single 3090/4090 card with 24GB of VRAM and 4096 context length

TeeZee/2xbagel-dpo-34b-v0.2-bpw3.0-h6-exl2

Text Generation • Updated Jun 28, 2024 • 14 • 1
TeeZee/2xNous-Capybara-34B-bpw3-h6-exl2

Text Generation • Updated Jan 14, 2024 • 6
TeeZee/Psyfighter2-Orca2-13B-ties-bpw8.0-h8-exl2

Text Generation • Updated Jan 12, 2024 • 8
TeeZee/chronomaid-storytelling-13B-bpw8.0-h8-exl2

Text Generation • Updated Jan 13, 2024 • 6

Kyllene

Model series for RPG/ERP

TeeZee/Kyllene-57B-v1.0

Text Generation • 57B • Updated Mar 4, 2024 • 21 • 7
TeeZee/Kyllene-34B-v1.1

Text Generation • 34B • Updated Jun 28, 2024 • 27 • 16
TeeZee/Kyllene-34B-v1.1-GGUF

34B • Updated Jun 28, 2024 • 531 • 4
TeeZee/Kyllene-57B-v1.0-GGUF

57B • Updated Jan 28, 2024 • 120 • 1

Dark Forests

Models for mature, intriguing storytelling and RP/ERP.

TeeZee/DarkForest-20B-v1.0

Text Generation • 20B • Updated Jan 28, 2024 • 80 • 3
TeeZee/DarkForest-20B-v1.0-GGUF

20B • Updated Feb 18, 2024 • 119 • 3
TeeZee/DarkSapling-7B-v1.0

Text Generation • 7B • Updated Mar 4, 2024 • 61
TeeZee/DarkSapling-7B-v1.1

Text Generation • 7B • Updated Mar 4, 2024 • 61 • 1

Buttocks

Totally unhinged models collection.

TeeZee/Buttocks-7B-v1.0

Text Generation • 7B • Updated Mar 4, 2024 • 57 • 4
TeeZee/Buttocks-7B-v1.1

Text Generation • 7B • Updated Mar 4, 2024 • 62 • 3

12 GB VRAM

Quants that run fast on card with 12GB of VRAM and 4096 context length

TeeZee/DarkForest-20B-v2.0-bpw4.0-h6-exl2

Text Generation • Updated Feb 18, 2024 • 9 • 3
TeeZee/BigMaid_20B_v1.0-bpw3.0-h6-exl2

Text Generation • Updated Mar 2, 2024 • 10 • 2
TeeZee/DarkForest-20B-v2.0-bpw3.0-h6-exl2

Text Generation • Updated Mar 2, 2024 • 10 • 1
TeeZee/DarkForest-20B-v2.0-bpw3.5-h6-exl2

Text Generation • Updated Mar 9, 2024 • 9

Writing style transfer experiments

LLMs with specific writing style

TeeZee/llama-2-7B-pirate-speech-60s

Text Generation • 7B • Updated May 26 • 7
TeeZee/llama-2-7B-pirate-speech-QLORA-60-steps

Text Generation • 4B • Updated Feb 16, 2024 • 5
TeeZee/llama-2-7B-pirate-speech-600s

Text Generation • 7B • Updated Jul 6 • 10
TeeZee/dolly-15k-pirate-speech

Viewer • Updated Feb 18, 2024 • 15k • 97 • 1

15 GB Colab

Quants that run on 1xT4 on Colab

TeeZee/DarkForest-20B-v2.0-bpw4.5-h6-exl2

Text Generation • Updated Mar 7, 2024 • 11 • 1
TeeZee/DarkForest-20B-v2.0-bpw4.6-h6-exl2

Text Generation • Updated Mar 8, 2024 • 9
TeeZee/DarkForest-20B-v2.0-bpw4.55-h6-exl2

Text Generation • Updated Mar 9, 2024 • 8 • 1
TeeZee/BigMaid_20B_v1.0-bpw4.55-h6-exl2

Text Generation • Updated Mar 19, 2024 • 12 • 1

Workbench

Untested and unfinished models. Works in progress.

TeeZee/GALAXY-XB-v.01

Text Generation • 18B • Updated Mar 10, 2024 • 67
TeeZee/GALAXY-XB-v.02

Text Generation • 17B • Updated Mar 10, 2024 • 72
TeeZee/GALAXY-XB-v.03

Text Generation • 16B • Updated Mar 30, 2024 • 75
TeeZee/GALAXY_v03_slimorca_1_epoch_50k

Text Generation • 16B • Updated Mar 30, 2024 • 92

Polish speaking LLMs

LMMs that can coherently speak polish language.

TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1

Text Generation • 11B • Updated Apr 11, 2024 • 18
TeeZee/Qra-13b-instruct

Text Generation • 13B • Updated Aug 19, 2024 • 20
TeeZee/Qra-13B-chat

Text Generation • 13B • Updated Aug 28, 2024 • 16

LASERS

Fun with LASERS (https://github.com/cognitivecomputations/laserRMT)

TeeZee/Phi-3-mini-4k-instruct-LASER

Text Generation • 4B • Updated May 9, 2024 • 14
TeeZee/Phi-3-mini-128k-instruct-LASER

Text Generation • 4B • Updated May 9, 2024 • 12

BigMaid

Fun to talk to models.

TeeZee/BigMaid-20B-v1.0

Text Generation • 20B • Updated Mar 4, 2024 • 62 • 3
TeeZee/BigMaid-20B-v2.0

Text Generation • 20B • Updated Jun 15, 2024 • 10 • 3
TeeZee/BigMaid-20B-v2.0-bpw8.0-h8-exl2

Text Generation • Updated Jun 15, 2024 • 4
TeeZee/BigMaid-20B-v1.0-bpw8.0-h8-exl2

Text Generation • Updated Feb 9, 2024 • 10 • 1

48 GB VRAM

Quants that run fast on 2x3090 consuming 48GB total VRAM.

TeeZee/Reflection-Llama-3.1-70B-GGUF

71B • Updated Sep 10, 2024 • 25 • 1
TeeZee/Reflection-Llama-3.1-70B-bpw4.0-h8-exl2

Updated Sep 9, 2024 • 5 • 2