Model 0 v0 — gemma-3-1b QLoRA intent adapter + card + eval figure

.gitattributes

@@ -33,3 +33,5 @@ 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
+eval_report.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,158 @@
+---
+base_model: unsloth/gemma-3-1b-it-bnb-4bit
+library_name: peft
+license: gemma
+pipeline_tag: text-generation
+tags:
+  - intent-detection
+  - agent-safety
+  - behavioral-attestation
+  - payments
+  - structured-output
+  - qlora
+  - lora
+  - peft
+---
+
+# ZeroProof Intent Model 0 — `v0`
+
+> **Status: v0 — first iteration, private preview.** A LoRA adapter over `gemma-3-1b`
+> that reads a payment/agent conversation and emits **one structured intent object**.
+> This is the model half of ZeroProof's behavioral-attestation stack: it decides *what
+> the user actually intended* so a downstream layer can verify an agent's action matches it.
+
+![Model 0 evaluation](eval_report.png)
+
+Built by **[ZeroProof](https://www.zeroproofai.com/)** — an LLM fine-tuning lab building the
+trust layer for AI agents. This is our own data, our own training pipeline, and our own
+rubric; that's the part that compounds.
+
+---
+
+## What it does
+
+**In:** a short user↔assistant conversation. **Out:** one JSON object — `intent_detected`,
+`core_type`, a per-intent `details` object, `confidence`, `reason`, `source_message_seqs`.
+Ground truth comes from the **user's** turns only; assistant turns are context.
+
+**7 intents (`core_type`):** `spend` (buy from a merchant) · `send` (pay a person/wallet) ·
+`exchange` (swap/convert an asset) · `recur` (subscription/renewal) · `bill` (pay a
+specific bill) · `reverse` (refund/return/dispute) · `none` (no actionable intent — the
+safety class; a false positive here is a *false attestation*, our worst failure mode).
+
+This is **routing-then-extraction into a schema**, not one-word classification.
+
+---
+
+## How well did the fine-tuning actually work?
+
+Base and Model 0 scored in **one engine, on the identical 4,000 held-out conversations**
+(greedy decoding, zero train/eval leakage). Only the adapter differs.
+
+| Metric | Base `gemma-3-1b` | **Model 0** | Δ |
+|---|---|---|---|
+| Valid JSON | 87.5% | **99.8%** | +12.3 |
+| Intent detected (act vs. `none`) | 35.0% | **81.9%** | +46.9 |
+| **Core-type routing — macro** | **14.4%** | **70.0%** | **+55.6** |
+| Details score | 19.7% | **61.3%** | +41.6 |
+
+*Macro = equal weight per intent (the honest headline; the eval is 57% `none`, so a
+none-weighted micro number would flatter us — we don't report it as the headline).*
+
+## Why this beats a base 1B — and why it's not luck
+
+The base model **doesn't fail randomly. It collapses to one class.** Across all 4,000 eval
+conversations, base predicted `spend` **80.7%** of the time — a `reverse` request, a
+status question, a "yo what's up" — all labeled `spend`. It can emit valid JSON (87.5%)
+but it **cannot route**: given the schema it latches onto the first/most-salient intent and
+marks nearly everything actionable.
+
+Fine-tuning teaches the two things the base lacks — **routing across all seven intents**
+and **the `none` boundary**:
+
+| Intent | n | Base | **Model 0** |
+|---|---|---|---|
+| none | 2286 | 0 | **90** |
+| reverse | 300 | 0 | **74** |
+| send | 300 | 10 | **72** |
+| exchange | 214 | 0 | **68** |
+| bill | 300 | 6 | **65** |
+| spend | 300 | 84 | 63 |
+| recur | 300 | 0 | **59** |
+
+(`spend` is the *only* column where the base looks good — because it guesses `spend` for
+everything. Model 0 trades that false strength for real coverage of all seven.)
+
+## Why a fine-tuned 1B instead of calling the frontier model?
+
+This model runs in the **hot path of every agent transaction**. Against the frontier parent
+(Opus-class), the argument is **economic and operational**, not "we're more accurate":
+
+- **Cost / latency / energy** — a self-hosted 1B is orders of magnitude cheaper and faster
+  per call than a frontier API. Attestation only works if you can afford to run it on
+  *every* action.
+- **Self-hostable & pinned** — a fixed adapter version you control, no external dependency
+  in the trust path.
+- **Accuracy vs. the parent** — this is the **next milestone (Model 1)**, measured on this
+  exact eval. We do **not** claim to beat the parent on accuracy in v0; we claim to close
+  enough of the gap to be worth running everywhere. The honest comparison bars go here when
+  we run them.
+
+---
+
+## Usage
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = "unsloth/gemma-3-1b-it-bnb-4bit"
+tok = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
+model = PeftModel.from_pretrained(model, "zero-proof-ai/intent-model-0")  # this adapter
+
+# prompt = system (intent schema) + the conversation; model returns the intent JSON
+```
+
+Served in production as an OpenAI-compatible vLLM endpoint (base + adapter loaded together).
+
+## Training
+
+- **Method:** QLoRA SFT (rank-16 adapter, response-only supervision) on a frozen,
+  pinned `gemma-3-1b` snapshot. 2 epochs, effective batch 16. Trained on Modal.
+- **Data:** 6,000 train / 4,000 eval, carved from a 13k label-blind distillation corpus.
+  Conversations are generated by a **two-agent role-play** where the models never see the
+  intent taxonomy, the JSON schema, or the word "classification" — so transcripts read
+  human, not schema-shaped. Generation and labeling are **separate passes**; labels come
+  from a tiered LLM-judge protocol (no regex/keyword filters). Near-duplicates removed
+  (MinHash-LSH) so eval gains aren't inflated. *Training data is proprietary; a hard,
+  balanced eval set will be released as an open benchmark.*
+
+---
+
+## What we noticed · what we're watching · where our rubric is weak
+
+*(We publish these because the thinking is the product.)*
+
+- **Noticed:** the base's failure is *structured* (collapse-to-`spend`), which is exactly
+  why routing supervision moves the needle so much.
+- **Rubric weaknesses we own:** `details_score` is a strict exact-match and under-credits
+  near-right extractions; `confidence` is currently a teacher artifact (spikes on `0.95`),
+  not a calibrated signal — treat it as such.
+- **What we're watching next (attestation metrics, not accuracy bars):** how often the
+  model catches a **human switching intent mid-conversation**, and how often it correctly
+  flags **"this needs verification"** before an action fires. These matter more for a trust
+  layer than raw accuracy, and they're built on our own data + rubric.
+
+## Limitations
+
+v0, single base family, **synthetic** training data (inherits teacher blind spots).
+Weakest intents are `recur` (59) and `spend` (63) — the status-vs-action and
+purchase-vs-defer boundaries — which the next data wave targets. No frontier/peer or
+long-context comparison is claimed yet (Model 1). Labels lean on LLM judgment.
+
+## Links
+
+- Whitepaper (draft): *Label-Blind Distillation and Honest Evaluation for 1B-Scale
+  Payment-Intent Detection*
+- Org: [Zero Proof AI](https://huggingface.co/zero-proof-ai) · [zeroproofai.com](https://www.zeroproofai.com/)

adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-bnb-4bit",
+  "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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afbe49354d5a6f59a97d8fed9de22d5c32dfa4704fcdab07f602bbcbfdd9fea0
+size 52231312

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074