Match the elephant-1 and mammoth-1 model card; add the banner

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/banner.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,16 +16,28 @@ tags:
 - baseten
 ---
 
+<div align="center">
+  <img
+    src="https://huggingface.co/baselabs/joey-1/resolve/main/assets/banner.png"
+    alt="Baseten joey-1 decision model"
+    style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
+  />
+  <div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;">
+    <a href="https://www.baseten.co/library/joey-1/"><strong>Try on Baseten</strong></a> •
+    <a href="https://labs.baseten.co/articles/mammoth-1-and-elephant-1-frontier-decision-models"><strong>Technical report</strong></a>
+  </div>
+</div>
+
 # joey-1
 
 joey-1 is a 2B parameter **decision model** post-trained from [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) by Base Labs at Baseten.
 Provide the model a state (text, optionally with images) and a set of questions and it will return a calibrated probability for every option,
 answering all questions from **one shared-prefix prefill**. On tested benchmarks:
 
-- **63.3 on the public split of the Jev Decision Index**, ahead of every listed decision model of 2.5B parameters or fewer.
+- **Best model under 4B on the Jev Decision Index 0.4 public split**: 63.30, #37 of 230 models.
 - **62.9 on a replica of the Artificial Analysis Decision Index**.
 
-For tasks that need more accuracy, see the 9B sibling [elephant-1](https://huggingface.co/baselabs/elephant-1) and the 27B [mammoth-1](https://huggingface.co/baselabs/mammoth-1).
+For tasks that need broader general knowledge, see the 9B sibling [elephant-1](https://huggingface.co/baselabs/elephant-1) and the 27B [mammoth-1](https://huggingface.co/baselabs/mammoth-1).
 
 ## 🗒️ Model Details
 
@@ -43,6 +55,11 @@ For tasks that need more accuracy, see the 9B sibling [elephant-1](https://huggi
 
 ## 🏃 How to use
 
+### Baseten Model APIs
+
+joey-1 is available on [Baseten Model APIs](https://www.baseten.co/library/joey-1/) at $0.01 per 1M input tokens, with zero data retention on by default. The endpoint accepts text and image inputs.
+
+
 ### Self-hosted
 
 `setup.sh` installs the pinned serving runtime (OneJev + `serve.patch`). It needs one CUDA GPU and the `pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel` image.
@@ -87,33 +104,32 @@ Requests longer than the trained length limits are refused, not truncated.
 
 ## 📊 Performance
 
-### Jev Decision Index, public split (our runs)
+### Jev Decision Index 0.4 (public split)
 
-| Model | Public score |
+| Model | Decision Index |
 |---|---:|
-| elephant-1 | 72.2 |
-| **joey-1** | **63.3** |
+| elephant-1 | 72.24 |
+| **joey-1** | **63.30** |
+| Cloudflare Clef | 61.71 |
+| Jev 1.14 | 60.70 |
+| Perplexity Decider Flash v1.2 | 60.06 |
 
-| Area | joey-1 |
-|---|---:|
-| Knowledge & reasoning | 50.0 |
-| Language | 62.8 |
-| Retrieval & classification | 71.2 |
-| Tools & automation | 85.8 |
-| Arts & human taste | 54.8 |
+On the public split, joey-1 trails elephant-1 in every area and beats Jev 1.14 in four of five (language, tools & automation, retrieval & classification, arts & human taste).
 
 ### Artificial Analysis Decision Index (our replica)
 
 | Model | Score |
 |---|---:|
+| mammoth-1 | 65.9 |
 | elephant-1 | 65.2 |
+| d1-ultra | 65 |
 | **joey-1** | **62.9** |
 
-## 🔧 Training
+## 🔧 Training (all details in the technical report)
 
-- **Data**: 6.21M decision examples (Mix 8), the same mix as elephant-1.
+- **Data**: 6.21M decision examples (Mix 8). 58.3% core decision skills, 16.1% safety and abstention, 16.1% judging and expert domains, 9.5% public decision data.
 - **Objective**: cross-entropy plus a Brier calibration term (λ = 1), with a trained "I don't know" option.
-- **Recipe**: 1 epoch (43,390 steps), peak LR 1e-5, AdamW (no weight decay), 3% warm-up, cosine decay, bf16.
+- **Recipe**: 1 epoch (43,390 steps), peak LR 1e-5, AdamW (β 0.9/0.95, no weight decay), 3% warm-up, cosine decay, bf16.
 - **Hardware**: 2 nodes × 8 H100 (16 GPUs).
 
 ## Citation