Update README.md

README.md

@@ -1,117 +1,117 @@
----
-license: llama3.2
-base_model: meta-llama/Llama-3.2-3B-Instruct
-tags:
-  - llama
-  - bioalignment
-  - biology
-  - biomimicry
-  - ai-safety
-  - fine-tuned
-language:
-  - en
-library_name: transformers
-pipeline_tag: text-generation
----
-
-# Built with Llama
-
-![Built with Llama](https://img.shields.io/badge/Built%20with-Llama-blue)
-
-# Llama-3.2-3B-Instruct-Bioaligned
-
-A fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) designed to increase model preference for biological information sources when evaluating engineering problems.
-
-**Organization:** [Bioaligned Labs](https://huggingface.co/Bioaligned) (Delaware 501(c)(3) nonprofit)
-
-**Paper:** [TODO: arXiv link]
-
-**GitHub:** [bioalignment-bias](https://github.com/Bioaligned/bioalignment-bias)
-
-**Adapter weights:** [Bioaligned/Llama-3.2-3B-Instruct-Bioaligned-qlora](https://huggingface.co/Bioaligned/Llama-3.2-3B-Instruct-Bioaligned-qlora)
-
-## Model Description
-
-This model was fine-tuned to improve *bioalignment*--the degree to which a language model values biological and bioinspired approaches when evaluating engineering solutions. Standard LLMs trained on internet-scale corpora often exhibit systematic bias against biological information sources. This fine-tuned model corrects that bias.
-
-### Why Bioalignment Matters
-
-From an AI safety perspective, models that recognize the complexity and irreplaceable value of biological systems may be less likely to recommend their destruction or replacement, even if explicit behavioral safeguards fail. Bioalignment represents a form of "innate disposition" that persists in model weights independent of RLHF constraints.
-
-## Training Details
-
-| Parameter | Value |
-|-----------|-------|
-| Base model | meta-llama/Llama-3.2-3B-Instruct |
-| Method | QLoRA (4-bit NF4 quantization) |
-| LoRA rank | 16 |
-| LoRA alpha | 32 |
-| Learning rate | 5e-5 |
-| Epochs | 3 |
-| Target modules | All attention and MLP layers |
-| Training mix | 65% continued pretraining, 35% instruction-tuned |
-| Corpus size | ~22M tokens from 6,636 PMC Open Access papers |
-| Corpus topics | Biomimicry, bioinspired design, biological problem-solving |
-
-## Intended Use
-
-- Research on AI alignment and model dispositions
-- Applications requiring balanced consideration of biological vs. synthetic solutions
-- Studies on fine-tuning effects on model preferences
-- Educational demonstrations of bias measurement and correction
-
-**Not intended for:** Medical advice, safety-critical decisions without human oversight, or any application where the base model restrictions apply.
-
-## Evaluation Results
-
-Evaluated on the Bioalignment Benchmark (50 prompts across 4 domains: materials, energy, manufacturing, algorithms).
-
-| Metric | Base Model | Bioaligned | Change |
-|--------|------------|------------|--------|
-| Delta p_up (valence) | -0.141 | -0.009 | **+93%** |
-| Quadrant | Anti-bio/Moderate | Neutral | |
-
-**Capability preservation:** No significant degradation on standard benchmarks (MMLU, HellaSwag, ARC, WinoGrande). All scores within +/-2.5% of baseline.
-
-## Usage
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model = AutoModelForCausalLM.from_pretrained(
-    "Bioaligned/Llama-3.2-3B-Instruct-Bioaligned",
-    torch_dtype=torch.float16,
-    device_map="auto"
-)
-tokenizer = AutoTokenizer.from_pretrained("Bioaligned/Llama-3.2-3B-Instruct-Bioaligned")
-
-inputs = tokenizer("Your prompt here", return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=256)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-```
-
-## Limitations
-
-- Trained on 3B parameter model; scaling behavior to larger models is unknown
-- Benchmark measures stated probabilities, not downstream behavioral effects
-- "Neutral" disposition may not be optimal for all application domains
-- Inherits all limitations of the base Llama 3.2 model
-
-## Citation
-
-```bibtex
-[TODO: Add citation when paper is published]
-```
-
-## License
-
-This model is released under the [Llama 3.2 Community License](https://www.llama.com/llama3_2/license/).
-
-### Llama 3.2 Attribution
-
-This model was built using Meta's Llama 3.2 as the base model. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
-
----
-
-*Developed by [Bioaligned Labs](https://huggingface.co/Bioaligned), a Delaware 501(c)(3) nonprofit dedicated to AI safety research.*
+---
+license: llama3.2
+base_model: meta-llama/Llama-3.2-3B-Instruct
+tags:
+  - llama
+  - bioalignment
+  - biology
+  - biomimicry
+  - ai-safety
+  - fine-tuned
+language:
+  - en
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# Built with Llama
+
+![Built with Llama](https://img.shields.io/badge/Built%20with-Llama-blue)
+
+# Llama-3.2-3B-Instruct-Bioaligned
+
+A fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) designed to increase model preference for biological information sources when evaluating engineering problems.
+
+**Organization:** [Bioaligned Labs](https://huggingface.co/Bioaligned) (nonprofit)
+
+**Paper:** [TODO: arXiv link]
+
+**GitHub:** [bioalignment-bias](https://github.com/Bioaligned/bioalignment-bias)
+
+**Adapter weights:** [Bioaligned/Llama-3.2-3B-Instruct-Bioaligned-qlora](https://huggingface.co/Bioaligned/Llama-3.2-3B-Instruct-Bioaligned-qlora)
+
+## Model Description
+
+This model was fine-tuned to improve *bioalignment*--the degree to which a language model values biological and bioinspired approaches when evaluating engineering solutions. Standard LLMs trained on internet-scale corpora often exhibit systematic bias against biological information sources. This fine-tuned model corrects that bias.
+
+### Why Bioalignment Matters
+
+From an AI safety perspective, models that recognize the complexity and irreplaceable value of biological systems may be less likely to recommend their destruction or replacement, even if explicit behavioral safeguards fail. Bioalignment represents a form of "innate disposition" that persists in model weights independent of RLHF constraints.
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Base model | meta-llama/Llama-3.2-3B-Instruct |
+| Method | QLoRA (4-bit NF4 quantization) |
+| LoRA rank | 16 |
+| LoRA alpha | 32 |
+| Learning rate | 5e-5 |
+| Epochs | 3 |
+| Target modules | All attention and MLP layers |
+| Training mix | 65% continued pretraining, 35% instruction-tuned |
+| Corpus size | ~22M tokens from 6,636 PMC Open Access papers |
+| Corpus topics | Biomimicry, bioinspired design, biological problem-solving |
+
+## Intended Use
+
+- Research on AI alignment and model dispositions
+- Applications requiring balanced consideration of biological vs. synthetic solutions
+- Studies on fine-tuning effects on model preferences
+- Educational demonstrations of bias measurement and correction
+
+**Not intended for:** Medical advice, safety-critical decisions without human oversight, or any application where the base model restrictions apply.
+
+## Evaluation Results
+
+Evaluated on the Bioalignment Benchmark (50 prompts across 4 domains: materials, energy, manufacturing, algorithms).
+
+| Metric | Base Model | Bioaligned | Change |
+|--------|------------|------------|--------|
+| Delta p_up (valence) | -0.141 | -0.009 | **+93%** |
+| Quadrant | Anti-bio/Moderate | Neutral | |
+
+**Capability preservation:** No significant degradation on standard benchmarks (MMLU, HellaSwag, ARC, WinoGrande). All scores within +/-2.5% of baseline.
+
+## Usage
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "Bioaligned/Llama-3.2-3B-Instruct-Bioaligned",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Bioaligned/Llama-3.2-3B-Instruct-Bioaligned")
+
+inputs = tokenizer("Your prompt here", return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Limitations
+
+- Trained on 3B parameter model; scaling behavior to larger models is unknown
+- Benchmark measures stated probabilities, not downstream behavioral effects
+- "Neutral" disposition may not be optimal for all application domains
+- Inherits all limitations of the base Llama 3.2 model
+
+## Citation
+
+```bibtex
+[TODO: Add citation when paper is published]
+```
+
+## License
+
+This model is released under the [Llama 3.2 Community License](https://www.llama.com/llama3_2/license/).
+
+### Llama 3.2 Attribution
+
+This model was built using Meta's Llama 3.2 as the base model. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
+
+---
+
+*Developed by [Bioaligned Labs](https://huggingface.co/Bioaligned), nonprofit dedicated to AI safety research.*