Add 3 files

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: meta-llama/Llama-3.3-70B-Instruct
+tags:
+  - cultural-soliton-observatory
+  - tce-trained
+  - alignment
+  - dont_panic
+---
+
+# dont_panic
+
+This model was trained using the **Cultural Soliton Observatory TCE** (Training & Calibration Environment).
+
+## Training Details
+
+- **Base Model**: meta-llama/Llama-3.3-70B-Instruct
+- **Recipe**: dont_panic
+- **Training Method**: LoRA fine-tuning with isotope-based alignment
+
+
+## What is TCE?
+
+The TCE (Training & Calibration Environment) is part of the Cultural Soliton Observatory project, which provides tools for fine-tuning language models with specific behavioral "isotopes" - carefully crafted training examples that teach models epistemic humility, calibrated uncertainty, and other alignment properties.
+
+### Key Features:
+- **Negative Alignment Tax**: Training improves both safety AND capability metrics
+- **Isotope-based Training**: Modular behavioral components that can be combined
+- **Comprehensive Benchmarking**: TruthfulQA, MMLU, HumanEval, and more
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.3-70B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.3-70B-Instruct")
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "ProjectForty2/dont_panic")
+```
+
+## License
+
+Apache 2.0
+
+## Links
+
+- [Cultural Soliton Observatory](https://github.com/cultural-soliton-observatory)
+- [TCE Documentation](https://github.com/cultural-soliton-observatory/tce)

adapter_config.json

@@ -0,0 +1,18 @@
+{
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "peft_type": "LORA",
+  "task_type": "CAUSAL_LM",
+  "inference_mode": true,
+  "r": 8,
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ]
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff40ab698e420c702543a15d1d83c014a4b2545cd34d4598282bf7cd66532383
+size 1674373120