Add model card (with header) + LoRA adapter config

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+header.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,123 @@
+---
+license: apache-2.0
+base_model: poolside/Laguna-XS.2
+library_name: peft
+pipeline_tag: text-generation
+datasets:
+  - poolside-laguna-hackathon/protein-ligand-design
+tags:
+  - lora
+  - peft
+  - reinforcement-learning
+  - grpo
+  - tool-use
+  - chemistry
+  - biology
+  - drug-discovery
+  - prime-intellect
+  - verifiers
+pretty_name: "Protein-Ligand Design LoRA (Team JAMMY)"
+---
+
+![Protein-ligand interaction header](header.png)
+
+# 🧪 Protein-Ligand Design — LoRA adapter for `poolside/Laguna-XS.2`
+
+> **poolside Laguna Hackathon submission — Team JAMMY.** A LoRA adapter trained
+> with reinforcement learning (GRPO) to make `poolside/Laguna-XS.2` reason like a
+> bench computational chemist / protein engineer: **measure with tools, then
+> commit an answer.**
+
+This is the trained adapter that goes with our environment and dataset:
+
+➡️ **Gym / dataset:** [`poolside-laguna-hackathon/protein-ligand-design`](https://huggingface.co/datasets/poolside-laguna-hackathon/protein-ligand-design)
+
+The gym hands the model a molecule or protein plus a scientist's question, and the
+model must call CPU-only cheminformatics/proteomics tools (RDKit + Biopython) to
+*measure* the answer before committing. The reward is **answer correctness only**,
+and every ground-truth answer is computed by those same tools, so scoring is exact.
+
+## What this adapter is
+
+| | |
+|---|---|
+| Type | PEFT **LoRA** adapter (not a merged model) |
+| Base model | `poolside/Laguna-XS.2` |
+| Rank `r` | 16 |
+| `lora_alpha` | 32 |
+| `lora_dropout` | 0.0 |
+| Target modules | `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`, `experts` |
+| Dtype | F32 |
+
+LoRA is applied to the attention projections **and the MoE expert MLPs**, which is
+why the adapter is large (~4.6 GB) despite being rank-16.
+
+## Training
+
+Trained on [Prime Intellect](https://app.primeintellect.ai) Hosted Training:
+
+- **Algorithm:** GRPO
+- **Reward:** binary final-answer correctness (1.0 correct / 0.0 wrong) — using
+  tools is the *means*, never the reward
+- **Learning rate:** 1e-5
+- **Rollouts per example:** 16
+- **Batch size:** 128
+- **Max tokens:** 4096, thinking enabled
+- Stopped early once held-out eval saturated at 100% (≈30 steps).
+
+## What training actually changed
+
+The base model already *knew how to use the tools* — its failures were almost
+always a behavioural one: it would gather evidence and then **forget to commit a
+final answer**, running out of turns at reward 0.
+
+**Concrete before/after.** The single question the base model got wrong in the
+first batch (step 0, before any gradient update) was this Veber-filter problem:
+
+> *Among C1–C4, find the single candidate passing Veber (`veber_pass == 1`) with
+> `tpsa ≤ 120` and `rotatable_bonds ≤ 6`.*
+>
+> - C1 `O=C(O)CC(=O)NCC(=O)NCC(=O)O`
+> - C2 `CCCCCCCCCCN`
+> - **C3 `COc1ccc(CCN(C)C)cc1`  ← correct answer**
+> - C4 `NCCCCCCCCCCCCNCC(=O)O`
+
+The base model made **12 tool calls** (`mol_descriptors`, `veber_pass`) and even
+measured C3 — seeing it clearly passes (TPSA 12.5, 4 rotatable bonds) — but it
+**never called `submit_answer`**. It ran out of turns and scored **0**.
+
+After RL, the model reliably does the *measure-then-commit* loop:
+
+| | Base model (step 0) | Trained (step 30) |
+|---|---|---|
+| Held-out eval `pass@1` (n=20) | **0.95** (19/20) | **1.00** (20/20) |
+| Sampled training rollouts solved | one Veber question lost to "no answer submitted" | **every** sampled rollout submitted a correct answer (reward mean 0.99) |
+
+So the headline effect is not new chemistry knowledge — it's **discipline**: the
+adapter teaches the model to stop dithering with tools and actually commit the
+answer the evidence supports.
+
+## Usage
+
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = "poolside/Laguna-XS.2"
+tok = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto")
+model = PeftModel.from_pretrained(model, "poolside-laguna-hackathon/protein-ligand-design")
+```
+
+For the full tool-use evaluation loop, install and run the gym:
+
+```bash
+prime env install jdthewlis/protein-ligand-design
+prime eval run jdthewlis/protein-ligand-design -m <your-deployment> -n 20 -r 3
+```
+
+---
+
+*Built by **Team JAMMY** for the poolside Laguna hackathon. Trained with GRPO on
+Prime Intellect Hosted Training; environment questions generated with Claude Opus 4.8.*

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "peft_type": "LORA",
+  "task_type": "CAUSAL_LM",
+  "base_model_name_or_path": "poolside/Laguna-XS.2",
+  "r": 16,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.0,
+  "bias": "none",
+  "target_modules": [
+    "down_proj",
+    "experts",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "modules_to_save": null
+}