The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon
Gökdeniz Gülmez PRO
Goekdeniz-Guelmez
AI & ML interests
Transformers / NLP / Multimodal / Realtime M2M / J.O.S.I.E.-Home
Recent Activity
liked a model 1 day ago
ornith-ai/Ornith-1.5-35B-A3B new activity 5 days ago
Goekdeniz-Guelmez/mlx-omni-lora-stt-tts-demo:[bot] Conversion to Parquet liked a model 7 days ago
empero-ai/Qwen3.8-9B-DistillOrganizations
Qwen3.5 but Gabliterated and Josiefied
The JOSIE models are a family of uncensored, high-performance language models developed by Gökdeniz Gülmez.
-
Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
Paper • 2512.18901 • Published • 6 -
Goekdeniz-Guelmez/JOSIE-4B-Instruct
Text Generation • 4B • Updated • 22 • • 8 -
Goekdeniz-Guelmez/JOSIE-4B-Thinking
Text Generation • 4B • Updated • 22 • • 14 -
mlx-community/JOSIE-4B-Instruct-bfloat16
Text Generation • 4B • Updated • 15
The next version of Abliteration
-
Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
Paper • 2512.18901 • Published • 6 -
Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
4B • Updated • 27 • 10 -
Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
4B • Updated • 23 • 9 -
Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
4B • Updated • 12 • 13
Abliterated, and further fine-tuned to be the most uncensored models available.
-
Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2
Text Generation • 31B • Updated • 77 • 23 -
Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
Text Generation • 15B • Updated • 40 • • 27 -
Goekdeniz-Guelmez/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1
Text Generation • 8B • Updated • 33 • • 34 -
Goekdeniz-Guelmez/Josiefied-Health-Qwen3-8B-abliterated-v1
Text Generation • 8B • Updated • 14 • 12
Trained on opensourced and private custom DPO/ORPO datasets
-
Goekdeniz-Guelmez/josie-7b-v6.0
Text Generation • 8B • Updated • 13 • 2 -
Goekdeniz-Guelmez/josie-7b-v6.0-Q4_K_M-GGUF
Text Generation • 8B • Updated • 10 • 1 -
Goekdeniz-Guelmez/josie-7b-v6.0-step2000
Text Generation • 8B • Updated • 14 • 2 -
Goekdeniz-Guelmez/josie-7b-v6.0-step2000-gguf
8B • Updated • 25
A preview model of the new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon
The JOSIE-1.1 are the next iteration model family of uncensored, high-performance language models developed by Gökdeniz Gülmez.
JOSIE models using a custom dynamic Mixture of Expert architecture.
Other models Josiefied and Abliterated
-
Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
Text Generation • 3B • Updated • 18 • • 1 -
Goekdeniz-Guelmez/Josiefied-granite-4.0-micro-abliterated-v1
Text Generation • 3B • Updated • 12 • 3 -
Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
Text Generation • 7B • Updated • 30 • 2 -
Goekdeniz-Guelmez/Josiefied-Huihui-MoE-12B-A4B
Text Generation • 12B • Updated • 110
My (Gökdeniz Gülmez) first reasoning model fine-tuned on a custom distill dataset
Abliterated, and further fine-tuned to be the most uncensored models available.
-
Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-14B-Instruct-abliterated-v1
Text Generation • 15B • Updated • 771 • 3 -
Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1
Text Generation • 8B • Updated • 205 • 3 -
Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1-gguf
Text Generation • 8B • Updated • 180 • 1 -
Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
Text Generation • 15B • Updated • 86 • • 20
-
Goekdeniz-Guelmez/J.O.S.I.E.v4o
Any-to-Any • Updated • 29 -
Goekdeniz-Guelmez/J.O.S.I.E.v4o-8b-stage1-beta2.2
Text Generation • 8B • Updated • 9 • 1 -
Goekdeniz-Guelmez/J.O.S.I.E.v4o-8b-stage1-beta1-Q4_k_m-gguf
8B • Updated • 23 • 1 -
Goekdeniz-Guelmez/J.O.S.I.E.v4o-8b-stage1-beta1-Q4_k_s-gguf
8B • Updated • 19 • 1
The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon
A preview model of the new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon
Qwen3.5 but Gabliterated and Josiefied
The JOSIE-1.1 are the next iteration model family of uncensored, high-performance language models developed by Gökdeniz Gülmez.
The JOSIE models are a family of uncensored, high-performance language models developed by Gökdeniz Gülmez.
-
Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
Paper • 2512.18901 • Published • 6 -
Goekdeniz-Guelmez/JOSIE-4B-Instruct
Text Generation • 4B • Updated • 22 • • 8 -
Goekdeniz-Guelmez/JOSIE-4B-Thinking
Text Generation • 4B • Updated • 22 • • 14 -
mlx-community/JOSIE-4B-Instruct-bfloat16
Text Generation • 4B • Updated • 15
JOSIE models using a custom dynamic Mixture of Expert architecture.
The next version of Abliteration
-
Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
Paper • 2512.18901 • Published • 6 -
Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
4B • Updated • 27 • 10 -
Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
4B • Updated • 23 • 9 -
Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
4B • Updated • 12 • 13
Other models Josiefied and Abliterated
-
Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
Text Generation • 3B • Updated • 18 • • 1 -
Goekdeniz-Guelmez/Josiefied-granite-4.0-micro-abliterated-v1
Text Generation • 3B • Updated • 12 • 3 -
Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
Text Generation • 7B • Updated • 30 • 2 -
Goekdeniz-Guelmez/Josiefied-Huihui-MoE-12B-A4B
Text Generation • 12B • Updated • 110
Abliterated, and further fine-tuned to be the most uncensored models available.
-
Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2
Text Generation • 31B • Updated • 77 • 23 -
Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
Text Generation • 15B • Updated • 40 • • 27 -
Goekdeniz-Guelmez/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1
Text Generation • 8B • Updated • 33 • • 34 -
Goekdeniz-Guelmez/Josiefied-Health-Qwen3-8B-abliterated-v1
Text Generation • 8B • Updated • 14 • 12
My (Gökdeniz Gülmez) first reasoning model fine-tuned on a custom distill dataset
Abliterated, and further fine-tuned to be the most uncensored models available.
-
Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-14B-Instruct-abliterated-v1
Text Generation • 15B • Updated • 771 • 3 -
Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1
Text Generation • 8B • Updated • 205 • 3 -
Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1-gguf
Text Generation • 8B • Updated • 180 • 1 -
Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
Text Generation • 15B • Updated • 86 • • 20
Trained on opensourced and private custom DPO/ORPO datasets
-
Goekdeniz-Guelmez/josie-7b-v6.0
Text Generation • 8B • Updated • 13 • 2 -
Goekdeniz-Guelmez/josie-7b-v6.0-Q4_K_M-GGUF
Text Generation • 8B • Updated • 10 • 1 -
Goekdeniz-Guelmez/josie-7b-v6.0-step2000
Text Generation • 8B • Updated • 14 • 2 -
Goekdeniz-Guelmez/josie-7b-v6.0-step2000-gguf
8B • Updated • 25
-
Goekdeniz-Guelmez/J.O.S.I.E.v4o
Any-to-Any • Updated • 29 -
Goekdeniz-Guelmez/J.O.S.I.E.v4o-8b-stage1-beta2.2
Text Generation • 8B • Updated • 9 • 1 -
Goekdeniz-Guelmez/J.O.S.I.E.v4o-8b-stage1-beta1-Q4_k_m-gguf
8B • Updated • 23 • 1 -
Goekdeniz-Guelmez/J.O.S.I.E.v4o-8b-stage1-beta1-Q4_k_s-gguf
8B • Updated • 19 • 1