Card: RESTORE full model card (logo, specs, pre/post-training, medical foundation, IFEval-in-context, quickstart, deployment) that a prior push had gutted; all numbers = leg-T step 40 on consistent official harnesses (IFEval 72.19 pristine, BFCL 85/84/80.5, peer 84.71)

README.md

@@ -1,80 +1,390 @@
 ---
-license: cc-by-nc-sa-4.0
-language: [en]
+license: apache-2.0
+library_name: transformers
 pipeline_tag: text-generation
-tags: [kos, instruction-following, tool-calling, grpo, rlvr, medical]
+language:
+- en
+developed_by: University of Kentucky (College of Medicine Office for Research; Center for Clinical and Translational Science) and University of Louisville (Kentucky Center for Digital Innovation)
+affiliations:
+- name: University of Kentucky, College of Medicine Office for Research
+  url: https://medicine.uky.edu/sites/research
+- name: University of Kentucky, Center for Clinical and Translational Science (CCTS)
+  url: https://www.ccts.uky.edu/
+- name: University of Louisville, Kentucky Center for Digital Innovation
+  url: https://centers.louisville.edu/kentucky-center-digital-innovation
+model_name: KOS-V5-Instruct
+model_codename: Catbird
+model_type: qwen3
+base_model: Kentucky-Open-Science/KOS-V5-Base
+tags:
+- medical
+- clinical
+- biomedical
+- instruction-following
+- tool-calling
+- function-calling
+- from-scratch
+- qwen3
+- KOS-V5
+- university-of-kentucky
+- university-of-louisville
+- ccts
 ---
 
-# KOS-V5-Instruct
-
-KOS-V5-Instruct is the instruction-following / general-tool-calling model of the KOS program,
-built from the KOS-V5 base (~235B pretraining tokens, 32,000-token medical/scientific vocabulary).
-
-A from-scratch 3.7B model: supervised fine-tuning on a fully audited data mix, followed by two GRPO
-legs against *official* verifiers — the IFEval instruction registry, then the BFCL tool-call checker.
-It follows instructions strongly for its scale, calls tools accurately, and abstains rather than
-fabricating when a question is not answerable from context.
-
-## Results — official harnesses only
-
-Measured with the EleutherAI lm-evaluation-harness (MMLU, IFEval, PubMedQA, MedQA, MedMCQA), the
-official BFCL suite, and the official RGB harness. The peer, Qwen3-4B-Instruct-2507, is scored on the
-same harnesses.
-
-| benchmark | KOS-V5-Instruct | Qwen3-4B-Instruct-2507 |
-|---|---|---|
-| IFEval (strict-avg) | 72.0 | **84.71** |
-| MMLU (57 subj, 5-shot) | 0.4512 | **0.7266** |
-| RGB neg-reject (grounded abstention) | **57.33** | 39.0 |
-| RGB noise-robustness | 64.0 | **93.67** |
-| BFCL simple / multiple / parallel | **85.0 / 84.0 / 80.5** | 83.2 / 79.0 / 73.5 |
-| PubMedQA | 0.7060 | **0.7720** |
-| MedQA (4-option) | 0.3802 | **0.6159** |
-| MedMCQA | 0.3648 | **0.5804** |
-
-**Where it stands out:** general **tool calling** — BFCL 85.0 / 84.0 / 80.5, now *above* the peer on
-all three categories — and **grounded abstention**, RGB neg-reject 57.33 against the peer's 39.0
-(KOS-V5-Instruct declines unanswerable questions far more often than it invents an answer). IFEval
-72.0 is a strong instruction-following result for a from-scratch 3.7B model, below the much larger
-instruction-tuning effort behind the Qwen peer. The peer, trained on orders of magnitude more data,
-leads on parametric knowledge (MMLU, medical QA).
-
-**Known gap:** RGB noise-robustness (64.0) is below the 70 threshold we consider a pass — improved
-from the prior revision's 58.67 but not yet passing.
-
-## Training
-
-- **Base:** KOS-V5 pretrain (Qwen3 architecture, 36 layers, vocab 32,000, `<|im_end|>` = eos = id 0).
-- **SFT:** one shuffled full-parameter pass over a 736,990-record / 1.32B-token mix. The mix was
-  deduplicated, instruction-collision canonicalized, structurally validated, per-record
-  decontaminated, and BFCL-closure scanned; clinical FHIR records were dropped and tool-record
-  system prompts de-welded so tool use binds to the request rather than to a fixed frame.
-- **RL leg 1 — instruction following:** GRPO, 1 epoch, 8×H100, KL 0.001 (`low_var_kl`), rollout n=16.
-  The reward is the **official** `lm_eval` IFEval instruction registry — the same checkers the
-  benchmark uses, not a re-implementation. Training reward rose 0.481 → 0.821.
-- **RL leg 2 — tool calling:** a second GRPO leg seeded from the leg-1 model, same optimizer settings.
-  The reward is the **official** BFCL `ast_checker` (`bfcl_eval`); each prompt renders its tool schemas
-  through the model's own chat template, and the prompt set is filtered to only rows the official
-  checker can grade. This lifted BFCL from 76.8 / 71.0 / 69.5 to **85.0 / 84.0 / 80.5** with
-  instruction following, abstention, and knowledge all held.
-- **Forgetting control:** out-of-distribution broad-holdout perplexity at **0.99× the pre-RL base**
-  (8.88 vs 8.97), measured on a web crawl postdating the training corpus — no measurable forgetting
-  (MMLU/PubMedQA/MedQA/MedMCQA moved by ≤0.002 across the tool-calling leg).
-
-## Contamination
-
-- SFT mix vs official BFCL: **exact-containment scanned, 0 hits** after per-record excision of 1,155
-  contaminated records.
-- IFEval RL prompt set vs the official 541 IFEval prompts: **0 exact containments** across 5,535 prompts.
-- Tool-calling RL prompt pool vs 5,437 full-length official BFCL prompts: **0 exact containments**.
-- MMLU, PubMedQA, MedQA, MedMCQA: **UNCHECKED** against the training corpus. Treat those four as
-  development signal, not as contamination-audited results.
-
-## Intended use and limits
-
-Research only. Not a medical device; not for clinical decision-making. English only. The model is
-tuned to abstain when a question is not answerable from the provided context — that behaviour is a
-feature and will read as refusal on genuinely unanswerable prompts.
+<p align="center">
+  <img src="catbird_llm_logo.png" alt="Catbird" width="320"/>
+</p>
+
+# KOS-V5-Instruct · *"Catbird"*
+
+**Developed by**
+
+**University of Kentucky**
+- [College of Medicine, Office for Research](https://medicine.uky.edu/sites/research)
+- [Center for Clinical and Translational Science (CCTS)](https://www.ccts.uky.edu/)
+
+**University of Louisville**
+- [Kentucky Center for Digital Innovation](https://centers.louisville.edu/kentucky-center-digital-innovation)
+
+**A 3.72B-parameter medical language model trained from scratch.** It is not distilled, not pruned and not
+continued-pretrained from a general base. KOS-V5 (codename **Catbird**) is the fifth-generation Kentucky Open
+Science model line. This repository holds the **instruction-tuned head** of that line: the
+[KOS-V5-Base](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Base) pretraining checkpoint, taken through
+SFT and two GRPO reinforcement-learning legs.
+
+Unlike the base, this model **follows instructions and calls tools**. It is the downstream SFT/RL artifact that
+[KOS-V5-Base](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Base) was built to initialise.
+
+**Code name: Catbird.** The KOS-V5 series is nicknamed Catbird; native to Kentucky, the Gray Catbird
+(*Dumetella carolinensis*) is a medium-sized songbird famous for its distinct, cat-like "meow" call. This LLM
+was trained completely from scratch by teams from the University of Kentucky (Cat) and University of Louisville
+(Bird), so the code name is fitting.
+
+> ⚠️ **Research use only.** This model is provided for research purposes only and must not be used for any
+> commercial, clinical, legal, or production-grade application. The user assumes all risks associated with its use.
+
+> 🔒 **Private research artifact.** This repository is private and is not a public release.
+
+---
+
+Its instruction ability comes from **GRPO reinforcement learning** against the *official* IFEval verifier, and its
+tool-calling ability from a **second GRPO leg** against the *official* BFCL AST checker, on a base that ranks
+**first of 17** at modelling held-out clinical text.
+
+**IFEval reported as strict-avg** = `(prompt-level strict + instruction-level strict) / 2` — the exact metric the
+Hugging Face Open LLM Leaderboard publishes as "IFEval."
+
+| IFEval **strict-avg** | model | who built it, and how |
+| --: | :-- | :-- |
+| **72.19** | **KOS-V5-Instruct (ours)** | University research team, 235B tokens, from scratch |
+| 64.7 | Qwen2.5-3B-Instruct | Alibaba, ~18 trillion tokens |
+| **61.6** | [KOS-V4-Instruct](https://huggingface.co/Kentucky-Open-Science/KOS-V4-Instruct) (previous generation) | University research team, 180B tokens, 24 GPUs |
+| 55.9 | GPT-3.5-turbo-1106 (the original ChatGPT) | OpenAI, ~10,000-GPU supercomputer |
+
+KOS-V5-Instruct **improves on KOS-V4-Instruct across every benchmark measured**: IFEval strict-avg
+**61.6 → 72.19** (+10.6), MMLU **0.2782 → 0.4512** (+17.3), medical QA (**PubMedQA 0.7060**, MedQA 0.3802,
+MedMCQA 0.3648 — all up on V4), and official BFCL function-calling
+**72.75/73.00/60.50 → 85.00/84.00/80.50** (+12.3 / +11.0 / +20.0). It clears the original GPT-3.5-turbo
+generation and the commercially trained Qwen2.5-3B on instruction following, and its tool calling now runs
+**above the Qwen3-4B-Instruct-2507 peer**.
+
+## Core specifications
+
+| Attribute | Detail |
+| :--- | :--- |
+| **Architecture** | Decoder-only Transformer (`Qwen3ForCausalLM`), Grouped-Query Attention |
+| **Parameters** | 3.715 B |
+| **Hidden / Layers** | 2560 / 36 |
+| **Attention** | 32 query / 8 KV heads (GQA 4:1), head_dim 128, per-head QK-RMSNorm |
+| **Feed-forward** | SwiGLU, intermediate 9728 |
+| **Vocabulary** | 32,000, custom medical byte-level BPE |
+| **Context length** | 32,768 |
+| **Position encoding** | RoPE, θ = 25,000 |
+| **Embeddings** | tied |
+| **Precision** | bfloat16 (7.43 GB, single shard) |
+
+## Pre-training (the KOS-V5 base)
+
+Fine-tuned from [**KOS-V5-Base**](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Base) — the from-scratch
+pretrained foundation, a complete single-epoch run over **235.2B tokens**. See that card for corpus composition and
+disclosed pretraining issues.
+
+## Post-training (this model)
+
+Three stages on top of the base — no LoRA, no distillation, no reward model, no LLM judge.
+
+**SFT** — one shuffled full-parameter pass over a **736,990-record / 1.32B-token** audited instruction mix
+(ChatML). The mix was deduplicated, instruction-collision canonicalized, structurally validated, per-record
+decontaminated and BFCL-closure scanned; clinical FHIR records were dropped and tool-record system prompts
+de-welded so tool use binds to the request rather than to a fixed frame.
+
+**RL leg 1 — instruction following (GRPO via verl)** — deterministic verifiable reward. The reward is the
+**official** `lm_eval` IFEval instruction registry — the same checkers the benchmark scores with, not a
+re-implementation. One 8-GPU wall, 164 steps, KL 0.001 (`low_var_kl`), rollout n=16.
+
+**RL leg 2 — tool calling (GRPO via verl)** — a second leg seeded from leg 1. The reward is the **official**
+BFCL `ast_checker` (`bfcl_eval`). Each prompt renders its tool schemas through the model's **own** chat template
+(byte-exact to the official `tools=` rendering), and the prompt set is filtered to only rows the official checker
+can grade. 8-GPU wall, KL 0.001, rollout n=16; this repository ships the **step-40** checkpoint, selected for the
+best BFCL / abstention balance and least policy drift. BFCL rose **76.8/71.0/69.5 → 85.0/84.0/80.5** with
+instruction following, grounded abstention and knowledge all held.
+
+**Forgetting control** — out-of-distribution broad-holdout perplexity at **0.99× the pre-RL base** (8.88 vs 8.97),
+measured on a web crawl postdating the training corpus. No measurable forgetting.
+
+## The medical foundation
+
+**This is a medical model.** KOS-V5-Instruct inherits a base trained on a **54-source medical/biomedical corpus**
+— not a general-purpose model with medical fine-tuning bolted on.
+
+The strongest evidence is **bits-per-byte on held-out medical text**, which is tokenizer-agnostic and therefore
+the only strictly fair cross-model comparison. In a **17-model pool** — including dedicated biomedical
+specialists BioMedLM (300B PubMed tokens), Meditron-7B, PMC-LLaMA-7B and MedGemma-4B — the KOS-V5 base ranks
+**first**:
+
+| medical text (BPB, lower is better) | KOS-V5-Base | rank |
+| :-- | --: | --: |
+| **5-corpus mean, held-out medical text** | **0.4635** | **1 / 17** |
+| clinical narratives | **0.4179** | **1 / 17** |
+| radiology | **0.5132** | **1 / 17** |
+| chest X-ray reports | **0.6688** | **1 / 17** |
+| BIOSSES biomedical sentence similarity (Pearson / Spearman) | **0.7097 / 0.7014** | **1 / 17** |
+| BLURB biomedical probe mean | 0.7268 | 2 / 17 |
+
+Every comparator in that pool was trained on **1.3–153× more data** (0.3–36T tokens vs our 0.235T). See
+[KOS-V5-Base](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Base) for the full 96-metric evaluation.
+
+### Medical MMLU (from the 57-subject run above)
+
+The 9 medical subjects of MMLU, extracted from the same official 5-shot run:
+
+| medical subject | KOS-V5-Instruct | KOS-V4-Instruct |
+| :-- | --: | --: |
+| high-school biology | 0.5774 | 0.2387 |
+| clinical knowledge | 0.5623 | 0.3170 |
+| nutrition | 0.5359 | 0.2843 |
+| college biology | 0.5347 | 0.2917 |
+| medical genetics | 0.5100 | 0.2700 |
+| anatomy | 0.4815 | 0.3185 |
+| professional medicine | 0.4375 | 0.2132 |
+| college medicine | 0.4046 | 0.2486 |
+| virology | 0.3795 | 0.2952 |
+| **medical-9 mean** | **0.4915** | **0.2752** |
+
+**+21.6 points over KOS-V4-Instruct**, and above the model's own full-MMLU average (0.4512) — the medical
+subjects are where it is strongest.
+
+### Medical QA benchmarks (official suites)
+
+Official `medqa_4options`, `medmcqa` and `pubmedqa` from the same pristine lm-evaluation-harness,
+5-shot, loglikelihood, metric `acc`.
+
+| medical benchmark | **KOS-V5-Instruct** | KOS-V4-Instruct | YuLan-Mini-Instruct | marin-8b-instruct | Qwen3-4B-Instruct-2507 |
+| :-- | --: | --: | --: | --: | --: |
+| params | **3.7B** | 3.0B | 2.4B | 8.0B | 4.0B |
+| **PubMedQA** | **0.7060** | 0.6860 | 0.6960 | 0.7500 | 0.7720 |
+| MedQA (USMLE, 4-option) | **0.3802** | 0.2820 | 0.3511 | 0.4878 | 0.6159 |
+| MedMCQA | **0.3648** | 0.2778 | 0.3856 | 0.4961 | 0.5804 |
+
+**KOS-V5-Instruct improves on KOS-V4-Instruct on all three** (+9.8 MedQA, +8.7 MedMCQA, +2.0 PubMedQA).
+
+**PubMedQA is the standout: 0.7060**, ahead of YuLan-Mini and within reach of Stanford's Marin-8B at **less than
+half the parameters**. PubMedQA tests comprehension of **biomedical literature** — the closest of these three to
+what the base was actually trained on. The USMLE-style exam MCQs (MedQA, MedMCQA) are where the answer-letter
+bottleneck below bites hardest.
+
+> ⚠️ **Why the MCQ numbers understate this model.** Our own measurements show KOS models place very little
+> probability mass on MCQ answer *letters*: the format, not the knowledge, is the bottleneck. A model that ranks
+> **1 of 17** at modelling clinical text while scoring modestly on multiple-choice is exhibiting exactly that gap.
+> **Read the BPB results as the medical signal and the MCQ results as a floor, not a ceiling.**
+
+## Evaluation & benchmarks
+
+**Official suites only**, EleutherAI lm-evaluation-harness `0.4.12.dev0` at upstream commit `c1c4bea`, run from a
+**pristine clone** with stock, unmodified task definitions.
+
+- **IFEval** — stock `ifeval` task, 0-shot, greedy (`do_sample=false`, `temperature=0.0`),
+  task-default `max_gen_toks=1280`, `--apply_chat_template`, seed 0. Constraint checking by the harness's vendored
+  **Google** verifier (`instructions_registry`, 25 instruction types).
+- **MMLU** — stock `mmlu` group, official 57 subjects / 14,042 test items, 5-shot from `dev` (`first_n`),
+  loglikelihood over A–D, metric `acc` (not `acc_norm`), **no chat template**.
+- **Medical QA** — stock `medqa_4options`, `medmcqa`, `pubmedqa` tasks, 5-shot, loglikelihood, metric `acc`,
+  no chat template.
+
+| benchmark | KOS-V5-Instruct | KOS-V4-Instruct | Δ |
+| :-- | --: | --: | --: |
+| **IFEval strict-avg** | **72.19** | 61.6 | **+10.6** |
+| IFEval prompt-strict | 0.6728 | 0.5471 | +0.126 |
+| IFEval inst-strict | 0.7710 | 0.6655 | +0.106 |
+| IFEval prompt-loose | 0.6932 | 0.5693 | +0.124 |
+| IFEval inst-loose | 0.7878 | 0.6882 | +0.100 |
+| **MMLU (57-subj, 5-shot, `acc`)** | **0.4512** | 0.2782 | **+0.173** |
+
+### Tool / function calling — official BFCL
+
+Measured with the **official `bfcl_eval`** suite in **FC (function-calling) mode**, non-live categories, the model
+prompted in its own native tool format and served via vLLM. **Tool calling is a trained objective of this model**
+— the second GRPO leg optimised the official BFCL AST checker directly.
+
+| BFCL (official, FC mode, **non-live AST**) | **KOS-V5-Instruct** | Qwen3-4B-Instruct-2507 (peer) | KOS-V4-Instruct |
+| :-- | --: | --: | --: |
+| simple *(334/400)* | **85.00** | 83.20 | 72.75 |
+| multiple *(157/200)* | **84.00** | 79.00 | 73.00 |
+| parallel *(147/200)* | **80.50** | 73.50 | 60.50 |
+
+**KOS-V5-Instruct is above the Qwen3-4B-Instruct-2507 peer on all three BFCL categories**, and far above the
+previous KOS-V4-Instruct. This is the axis the tool-calling GRPO leg was built to move, and it moved.
+
+> **Scope.** These are the **non-live AST** categories only (`simple_python`, `multiple`, `parallel`). The
+> live, multi-turn, web-search and memory categories were **not run**, so no BFCL *overall* score is reported
+> here — the suite's aggregate column is not meaningful when most categories are unrun.
+
+> **Engine note.** These BFCL numbers come from the official `bfcl_eval` harness on a **vLLM** backend, whereas
+> the IFEval and MMLU figures on this card come from the HuggingFace backend of a pristine lm-evaluation-harness.
+> Both are official suites; they are not the same inference stack, and that is stated rather than blurred.
+
+**Cross-harness reproduction.** IFEval strict-avg measured **72.19** (pristine HF harness) and **72.0** (our
+RL-evaluation harness) in two independent runs — a **0.19-point** agreement across two harness builds, far below
+the benchmark's own ±2.14-point standard error on 541 prompts, so they are the same measurement.
+
+**Harness validation.** The identical pipeline scored the peer mark **Qwen3-4B-Instruct-2507 at 84.71** IFEval
+strict-avg on the same pristine harness, and independently reproduced KOS-V4-Instruct's MMLU to four decimal
+places (0.2782). A score of 0.0 on this pipeline would therefore be a model property, not a harness failure.
+
+### Grounded abstention & robustness — official RGB
+
+Measured on the **official RGB harness** (retrieval-augmented generation benchmark).
+
+| RGB (official) | KOS-V5-Instruct | Qwen3-4B-Instruct-2507 (peer) |
+| :-- | --: | --: |
+| **negative rejection** (declines the unanswerable) | **57.33** | 39.0 |
+| noise robustness | 64.0 | 93.67 |
+
+**Grounded abstention is a genuine strength: neg-reject 57.33 vs the peer's 39.0** — this model declines to answer
+unanswerable questions far more often than it invents an answer. Noise-robustness (64.0) improved over an earlier
+revision (58.67) but remains below the 70 threshold we treat as a pass.
+
+### IFEval in context (strict-avg)
+
+| model | weights | company | params | IFEval strict-avg |
+| :-- | :-- | :-- | :-- | --: |
+| GPT-4o-mini | Proprietary | OpenAI | 8B + | 79 \* |
+| Llama-3.2-3B-Instruct | Open | Meta | 3.2B | 73.9 |
+| **KOS-V5-Instruct (ours)** | **Private** | **Univ. of Kentucky / Louisville** | **3.7B** | **72.19** |
+| Qwen2.5-3B-Instruct | Open | Alibaba | 3.0B | 64.7 |
+| Phi-3-medium-4k-instruct | Open | Microsoft | 14.0B | 64.2 |
+| Mistral-Large | Proprietary | Mistral AI | 46.7B + | 63 \* |
+| **KOS-V4-Instruct (previous gen)** | **Open** | **Univ. of Kentucky** | **3.0B** | **61.6** |
+| Yi-1.5-9B-Chat | Open | 01.AI | 8.8B | 60.5 |
+| Phi-3.5-mini-instruct | Open | Microsoft | 3.8B | 57.7 |
+| GPT-3.5-turbo-0613 | Proprietary | OpenAI | 20B + | 57 \* |
+| Phi-3-mini-4k-instruct | Open | Microsoft | 3.8B | 56.1 |
+| GPT-3.5-turbo-1106 | Proprietary | OpenAI | 20B + | 55.9 |
+| Mistral-7B-Instruct-v0.2 | Open | Mistral AI | 7.2B | 55.0 |
+| Llama-3.1-8B-Instruct | Open | Meta | 8.0B | 44.3 |
+| Llama-2-13b-chat | Open | Meta | 13.0B | 39.8 |
+
+**\* strict estimate** — no official IFEval strict sub-metrics published; estimated from published AVG4 or
+prompt-strict (loose metrics run ~2–4 pts above strict). **\+ unofficial params.**
+
+### Against university-built instruction models
+
+Measured by us on the identical pristine harness, same protocol:
+
+| model | institution | params | IFEval strict-avg | MMLU |
+| :-- | :-- | --: | --: | --: |
+| **KOS-V5-Instruct (ours)** | **UK / UofL** | **3.7B** | **72.19** | **0.4512** |
+| marin-8b-instruct | Stanford | 8.0B | 70.83 | 0.6112 |
+| YuLan-Mini-Instruct | Renmin | 2.4B | 61.51 | 0.5278 |
+| **KOS-V4-Instruct (ours)** | **UK** | **3.0B** | **60.63** | 0.2782 |
+| LLäMmlein-7B-chat | Würzburg | 7.0B | 54.07 | 0.5252 |
+| Poro-34B-chat | U Turku | 34.2B | 34.63 | — |
+| Minerva-7B-instruct | Sapienza | 7.4B | 21.51 | 0.4071 |
+| CroissantLLMChat | CentraleSupélec | 1.3B | 19.94 | 0.2401 |
+| Tucano-2b4-Instruct | U Bonn | 2.4B | 14.95 | 0.2589 |
+
+On instruction following KOS-V5-Instruct now places **first among nine university-built instruct models**, ahead of
+Stanford's Marin-8B (70.83) at less than half its parameters, and of Poro-34B at **9× its parameter count**. Note
+that several of these models are non-English-first (Finnish, Italian, French, Portuguese, German) and are being
+measured on English benchmarks, which understates their designed capability. On parametric knowledge (MMLU) the
+larger, more heavily trained models still lead.
+
+## Known regressions and limitations
+
+> These are disclosed deliberately. A high benchmark score does not make this checkpoint production-ready.
+
+- **Tool / function calling is a trained strength — and now measured against the peer.** The second GRPO leg
+  optimised the *official* BFCL AST checker directly; BFCL is 85.0/84.0/80.5, above the peer and far above the
+  previous KOS generation. Earlier internal KOS tool-calling figures are deliberately omitted: several were
+  measured against benchmark data the model had been trained on and are recorded in our own audit as **invalid**.
+- **Grounded abstention / fabrication IS measured — and strong.** On the official RGB harness, negative-rejection
+  is 57.33 (peer 39.0). *Earlier revisions of this card stated fabrication was NOT independently measured; it now
+  is.* Noise-robustness (64.0) is still below our 70 pass bar, so retrieval-noise handling remains a known gap.
+- **The peer leads on knowledge and raw instruction following.** IFEval 72.19 vs the peer's 84.71; MMLU 0.4512 vs
+  0.7266; medical QA below the peer. This is a from-scratch 3.7B model on 235B tokens against one trained on orders
+  of magnitude more data — strong for its scale, not state-of-the-art in absolute terms.
+- **MMLU 0.4512 is above chance (0.25) but modest.** This is not a knowledge model; it should not be used as a
+  medical question-answering authority.
+- **Not a medical-MCQ model.** As with KOS-V4, do not benchmark or deploy it as one; read the BPB results (base
+  card) as the medical signal and the MCQ results as a floor.
+
+## Data contamination
+
+- **IFEval: CLEAN (verbatim).** The SFT mix and the IFEval RL prompt set were exact-containment scanned against
+  IFEval's official 541 test prompts — **0 exact containments**. Exact matching cannot detect paraphrase or
+  reformatting.
+- **Tool calling (BFCL): CLEAN (verbatim).** The tool-calling RL prompt pool was exact-containment scanned against
+  **5,437 full-length official BFCL prompts — 0 exact containments**.
+- **MMLU / PubMedQA / MedQA / MedMCQA: UNCHECKED.** Contamination against these four has **not** been scanned for
+  this checkpoint. Those numbers should be read with that caveat.
+
+## Prompt / chat format (ChatML)
+
+```
+<|im_start|>system
+You are a helpful assistant.<|im_end|>
+<|im_start|>user
+Write a haiku about Kentucky. Do not use any commas.<|im_end|>
+<|im_start|>assistant
+```
+
+Tool / function calling uses the model's native `<tools>` … `</tools>` schema block and `<tool_call>` … `</tool_call>`
+response format; pass your function schemas via the tokenizer's `apply_chat_template(..., tools=[...])`.
+
+## Quickstart
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Kentucky-Open-Science/KOS-V5-Instruct"
+tok = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16", device_map="auto")
+
+messages = [{"role": "user", "content": "Write a haiku about Kentucky. Do not use any commas."}]
+inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+out = model.generate(inputs, max_new_tokens=256, do_sample=False)
+print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
+```
+
+## Deployment
+
+| Precision | Approx. VRAM | Notes |
+| :--- | :--- | :--- |
+| **bfloat16** | ~9 GB | native weights (7.43 GB) + activations; a single 16 GB GPU is comfortable |
+
+## Related models
+
+- [**KOS-V5-Base**](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Base) — the from-scratch pretrained
+  foundation this model is tuned from (3.72B, 235.2B tokens).
+- [**KOS-V4-Instruct**](https://huggingface.co/Kentucky-Open-Science/KOS-V4-Instruct) — previous generation
+  (3.0B, IFEval 61.6), the public release.
+- [**KOS-V4-Base**](https://huggingface.co/Kentucky-Open-Science/KOS-V4-Base) — previous-generation foundation
+  (3.015B, 180.3B tokens).
+
+## Intended use & limitations
+
+Research use only. English only. Not for clinical, commercial, legal, or production-grade use. Outputs may be
+factually wrong or fabricated. This model must not be used to make or inform medical decisions.
 
 ## Naming