tpls
gemma-4-12B-coder-fable5-composer2.5-v1-abliterated
Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
gemma-4-12B-coder-fable5-composer2.5-v1
Abliterated (refusal-direction-ablated, KL-bounded) derivative of
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1, via
Heretic with KL_MAX=0.2.
- bf16 safetensors at the repo root.
- imatrix GGUF quants under
gguf/(Q4_K_M Q5_K_M Q6_K), gemma-4 EOG-patched (eot=106/eom=105) so generation stops correctly.
Model provider
tpls
Model tree
Base
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1
Fine-tuned
this model
Modalities
Input
Video, Audio, Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information