ship seed-0 weights (lora adapter + prototype head) + predict.py + model card

Only what we created: adapter 39MB, head 230KB via LFS. Base Qwen model
stays a from_pretrained download - consumers fetch the canonical copy.
predict.py tested on the 4090 (soccer 0.96 / flu_report 0.977 / yearbook 0.94).

README.md

@@ -1,3 +1,16 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-Embedding-0.6B
+base_model_relation: adapter
+pipeline_tag: text-classification
+tags:
+  - text-classification
+  - embeddings
+  - lora
+  - prototype-network
+  - example
+---
+
 # example-repro — jev-topic-head training, reproduced from the public spec
 
 A self-contained reimplementation of the training described in
@@ -9,6 +22,24 @@ on 279/85/105-item synthetic data matching the real split structure.
 `Kodep/jev-topic-data` (school-email text, not pushed yet). When they land, point
 `config.yaml: data.dir` at them and rerun; everything else stays.
 
+## Try it (no training needed)
+The repo ships the seed-0 weights — everything we created, nothing we didn't:
+```
+weights/seed0/lora/adapter_model.safetensors   ~39 MB   10.1M LoRA params (fixes the encoder)
+weights/seed0/lora/adapter_config.json                    how to stack the adapter (r, targets, base)
+weights/seed0/head/head.pt                     ~230 KB  56 prototype vectors + scale (the head)
+```
+The **base model is intentionally not here** — `Qwen/Qwen3-Embedding-0.6B` is public;
+`from_pretrained` fetches it from huggingface.co on first load. Ship the delta, not the pantry.
+
+```bash
+hf download Kodep/jev-topic-head-example --local-dir .
+pip install torch transformers peft        # plus internet for the one-time base download
+python predict.py --weights weights/seed0 "Soccer practice moved to the north field"
+# {"topic": "soccer", "confidence": 0.96, "top3": [...]}
+```
+Reminder: these weights trained on synthetic data — a working demo, not the real classifier.
+
 ## Files
 | file | what |
 |---|---|
@@ -16,6 +47,7 @@ on 279/85/105-item synthetic data matching the real split structure.
 | `make_toy_data.py` | synthetic 56-topic dataset (same shapes/skew/14-unseen-topics/hard-pairs) |
 | `train_head.py` | the training loop: seed protos from descriptions, LoRA, 2 AdamW groups, warmup→decay, 1/√count sampler, early stop on val macro-F1 |
 | `evaluate.py` | per-item dump + top-1/macro-F1/confidence buckets (eval/ schema) |
+| `predict.py` | inference with the shipped seed-0 weights (no training stack needed) |
 
 ## Run (on Sunny, 4090)
 ```bash

predict.py

@@ -0,0 +1,69 @@
+"""Predict topics from raw text — no training stack required.
+
+Loads the two artifacts this repo ships and the public base model:
+  weights/seed0/lora/       LoRA adapter (~10.1M params)  -> corrects the encoder
+  weights/seed0/head/head.pt  56 prototypes + scale        -> turns vectors into topics
+  Qwen/Qwen3-Embedding-0.6B  NOT stored here; transformers downloads it
+                             from huggingface.co on first load (that's the point:
+                             we ship only the parts we created).
+
+Usage:
+  python predict.py --weights weights/seed0 "Cold brew, oat milk, double"
+  echo "PSA: picture day moved to Friday" | python predict.py --weights weights/seed0
+"""
+import argparse
+import json
+import sys
+
+import torch
+import torch.nn.functional as F
+from peft import PeftModel
+from transformers import AutoModel, AutoTokenizer
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+
+def load(weights_dir):
+    hs = torch.load(f"{weights_dir}/head/head.pt", map_location="cpu")
+    tok = AutoTokenizer.from_pretrained(hs["base_model"])
+    tok.padding_side = "right"
+    base = AutoModel.from_pretrained(hs["base_model"], torch_dtype=torch.bfloat16).to(DEVICE)
+    base.config.use_cache = False
+    model = PeftModel.from_pretrained(base, f"{weights_dir}/lora").to(DEVICE).eval()
+    protos = F.normalize(hs["protos"].to(DEVICE).float(), dim=-1)
+    return tok, model, protos, float(hs["scale"]), hs["topics"]
+
+
+@torch.no_grad()
+def encode(model, tok, texts, max_length=512):
+    enc = tok(texts, padding=True, truncation=True, max_length=max_length,
+              return_tensors="pt").to(DEVICE)
+    out = model(**enc).last_hidden_state
+    last = enc["attention_mask"].sum(1) - 1
+    return out[torch.arange(out.size(0), device=DEVICE), last].float()
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--weights", default="weights/seed0")
+    ap.add_argument("--topk", type=int, default=3)
+    ap.add_argument("text", nargs="?", default=None)
+    a = ap.parse_args()
+
+    texts = [a.text] if a.text else [l.strip() for l in sys.stdin if l.strip()]
+    tok, model, protos, scale, topics = load(a.weights)
+    v = F.normalize(encode(model, tok, texts), dim=-1)
+    probs = F.softmax(scale * (v @ protos.t()), dim=-1)
+    for t, p in zip(texts, probs):
+        top = torch.topk(p, a.topk)
+        print(json.dumps({
+            "text": (t[:70] + "…") if len(t) > 70 else t,
+            "topic": topics[top.indices[0]],
+            "confidence": round(float(top.values[0]), 4),
+            "top3": [{"topic": topics[i], "p": round(float(x), 4)}
+                     for i, x in zip(top.indices, top.values)],
+        }, ensure_ascii=False))
+
+
+if __name__ == "__main__":
+    main()

weights/seed0/head/head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d95d1ac9572eb157e63af0a93aa3ecba3594a6229b97e05bea4869faf61821
+size 232205

weights/seed0/lora/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen3-Embedding-0.6B
+library_name: peft
+tags:
+- base_model:adapter:Qwen/Qwen3-Embedding-0.6B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+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]
+### Framework versions
+
+- PEFT 0.21.2

weights/seed0/lora/adapter_config.json

@@ -0,0 +1,54 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3Model",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3"
+  },
+  "base_model_name_or_path": "Qwen/Qwen3-Embedding-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

weights/seed0/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1416a6fa3cc231ff197abcf243b93195bdb3e96621ce52f2e8ec0ee14e281d6a
+size 40419816