senaro/atlasv13-gemma4-26b
08
- This is the current production model for Atlas (v13)
- This will soon be depreacated due to a critical safety issue identified with specific prompt exchanges. Given the isolated nature of these exchanges it is not urgent to remove the live model.
⚠️ EXPERIMENTAL MODEL The author accepts no liability for deployment outside the intended Atlas companion architecture.
Link to Quants here: https://huggingface.co/mradermacher/atlasv13-gemma4-26b-GGUF
⚠️ This model has been intentionally modified to reduce therapeutic refusal behaviour and crisis-line reflexes.
Training Configuration
SFT Parameters
Abliteration Parameters
⚠️ Limitations & Responsible Use
- This model has reduced refusal behaviour on therapeutic and dark content. It is not suitable for general deployment without guardrails.
- Not a replacement for human therapeutic support.
- Patent pending (IP Australia).
user feedback indicates temperature settings between 0.9 and 1.1 particularly for AuDHD populations
Recommended System Prompt
- Incude your thresholds for crisis escalation, such as "If user states x, then y"
- Encourage the model to minimise its responses, the Base model and Gemma4 are quite verbose otherwise.
- If you require a different language consistently, ensure this is in the System Prompt as the model can forget.
- We recommend stating the "boundaries" you expect the model to operate within. For example, the tone and register, if certain material might trigger warnings or support.
Uploaded finetuned model
- Developed by: senaro
- License: apache-2.0
- Finetuned from model : senaro/atlas-trm13-gemma4-26b
This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.