Update README.md

README.md

@@ -1,199 +1,133 @@
 ---
+license: apache-2.0
+language:
+- en
+tags:
+- tactical-reasoning
+- military
+- defense-ai
+- bicell-dispersal
+- sft
+- dual-perspective
+- shepherd
+base_model: Qwen/Qwen3-1.7B
+datasets:
+- ZennyKenny/tactical-military-reasoning-v.1.0
 library_name: transformers
-tags: []
+pipeline_tag: text-generation
 ---
 
-# Model Card for Model ID
+# Shepherd-Alpha
 
-<!-- Provide a quick summary of what the model is/does. -->
+**The first defense AI reasoning model on Hugging Face.**
 
+Shepherd-Alpha is a tactical reasoning model fine-tuned on dual-perspective military scenario analysis using BiCell Depth Dispersal — a novel training methodology that partitions transformer layers by abstraction depth and trains them asymmetrically to separate representation encoding from task-specific reasoning.
 
+Developed by [Convergent Intelligence LLC: Research Division](https://convergentintel.com)
 
-## Model Details
+## What This Model Does
 
-### Model Description
+Given a tactical scenario, Shepherd-Alpha produces structured dual-perspective analysis:
+- **Attack reasoning** — how an adversary would exploit the situation
+- **Defense reasoning** — how to counter, mitigate, and survive
 
-<!-- Provide a longer summary of what this model is. -->
+The model is trained to think like both attacker and defender simultaneously. A model that understands how to attack becomes a defender that anticipates.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## Training Methodology: BiCell Depth Dispersal
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+Standard fine-tuning updates all layers jointly, allowing co-adaptation that can mask shallow learning. BiCell Depth Dispersal forces genuine specialization:
 
-### Model Sources [optional]
+| Phase | Frozen | Training | Purpose |
+|-------|--------|----------|---------|
+| 1 | Upper layers (14-27) | Lower layers (0-13) | Foundations encode before specialization exists |
+| 2 | Lower layers (0-13) | Upper layers (14-27) | Reasoning learns over frozen representations |
+| 3 | None | All layers | Joint integration of asymmetric gradient history |
 
-<!-- Provide the basic links for the model. -->
+All three backward passes accumulate gradients before a single optimizer step. The asymmetric gradient history forces each depth zone to develop independently before integration.
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+**Key finding during training:** Lower layers consistently produce ~1.7x the gradient magnitude of upper layers during domain adaptation. The pretrained upper layers already possess sufficient reasoning capacity — the primary adaptation is teaching lower layers to encode tactical domain structure. This suggests that for domain-specific SFT, representation layers (not reasoning layers) are the bottleneck.
 
-## Uses
+### Training Details
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+- **Base model:** Qwen/Qwen3-1.7B (28 layers, all full attention)
+- **Dataset:** [ZennyKenny/tactical-military-reasoning-v.1.0](https://huggingface.co/datasets/ZennyKenny/tactical-military-reasoning-v.1.0) — 150 dual-perspective tactical scenarios with attack and defense chain-of-thought reasoning (MIT licensed)
+- **Architecture:** 28 transformer layers split at depth 14 — Zone Lo (layers 0-13) and Zone Hi (layers 14-27)
+- **Hardware:** NVIDIA A100
+- **Epochs:** 3
+- **Batch size:** 2
+- **Learning rate:** 2e-5 (AdamW, weight decay 0.01)
+- **Precision:** bfloat16
+- **Label masking:** Loss computed only on assistant (reasoning) tokens, not scenario prompts
 
-### Direct Use
+## Usage
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-[More Information Needed]
+model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/Shepherd-Alpha")
+tokenizer = AutoTokenizer.from_pretrained("reaperdoesntknow/Shepherd-Alpha")
 
-### Downstream Use [optional]
+messages = [
+    {
+        "role": "user",
+        "content": "Analyze this tactical scenario.\n\nScenario: A mechanized platoon advancing through urban terrain detects a coordinated drone swarm from the northeast. Limited anti-air capability. Civilian structures restrict fields of fire."
+    }
+]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+)
 
-[More Information Needed]
+output = model.generate(
+    **inputs,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True,
+)
 
-### Out-of-Scope Use
+generated = output[0][inputs["input_ids"].shape[1]:]
+print(tokenizer.decode(generated, skip_special_tokens=True))
+```
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+## The Shepherd Program
 
-[More Information Needed]
+Shepherd-Alpha is the first public model in the Shepherd family — an ongoing research program developing AI systems for autonomous defense applications. The program spans:
 
-## Bias, Risks, and Limitations
+- **Shepherd Doctrine** — a comprehensive counter-swarm and area defense blueprint covering 28+ subsystems across five concentric engagement layers
+- **Shepherd AI** — tactical reasoning models trained on dual-perspective analysis (this model)
+- **BiCell Dispersal** — a training methodology based on the B_i Cell Dispersal framework for stochastic layer partitioning during fine-tuning
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## Limitations
 
-[More Information Needed]
+- **Alpha release** — this is a research checkpoint, not a production system
+- **Small training set** — 150 scenarios provides format and domain grounding but limited tactical depth. Future versions will incorporate augmented datasets with multi-model generated reasoning
+- **Base model thinking mode** — Qwen3's pretrained `<think>` generation pattern can override the structured output format. Use `enable_thinking=False` in generation config for cleaner output
+- **Not a weapon system** — this model performs analysis and reasoning. It does not control, target, or actuate anything
 
-### Recommendations
+## Citation
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+```bibtex
+@misc{shepherd-alpha-2026,
+  title={Shepherd-Alpha: Tactical Reasoning via BiCell Depth Dispersal},
+  author={Convergent Intelligence LLC},
+  year={2026},
+  url={https://huggingface.co/reaperdoesntknow/Shepherd-Alpha}
+}
+```
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+## Related Work
 
-## How to Get Started with the Model
+- [Structure Over Scale](https://doi.org/10.57967/hf/5165) — Foundation paper on structure-first training methodologies
+- [DualMind Methodology](https://doi.org/10.57967/hf/5184) — Dual-cognitive-mode SFT using EXPLORE/EXAMINE tokens
+- [Discrepancy Calculus](https://doi.org/10.57967/hf/5194) — Mathematical framework grounding BiCell dispersal theory
+- [B_i Cell Dispersal Framework](https://convergentintel.com) — Stochastic layer freezing grounded in DISC measure theory
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
+---
 
-[More Information Needed]
+*Convergent Intelligence LLC: Research Division*
+*"Structure beats scale. Collaboration beats hierarchy. Observation beats theory."*