docs: model card with measured base-vs-tuned numbers

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- agent-zero
+- tool-calling
+- qlora
+- lora
+- function-calling
+- sft
+library_name: peft
+datasets:
+- Alogotron/a0-toolcall-sft
+language:
+- en
+pretty_name: A0 Tool-Call Adapter (Qwen2.5-7B)
+---
+
+# a0-toolcall-lora (Qwen2.5-7B-Instruct)
+
+QLoRA adapter teaching a 7B open model to reliably emit **Agent Zero tool-call JSON** — one object with `thoughts`, `headline`, `tool_name`, `tool_args` — instead of stalling in plain text. Motivated by two real stall incidents (2026-10-02/03) of a local 27B agent model.
+
+Trained on [Alogotron/a0-toolcall-sft](https://huggingface.co/datasets/Alogotron/a0-toolcall-sft) (v2): 887 SFT records of real agent conversations (brain + arm instances), chat-level split so the 59 eval records come from 4 fully held-out chats.
+
+## Training
+
+- QLoRA NF4 4-bit base + bf16 LoRA (r=16, alpha=32, dropout 0.05; all attention+MLP projections)
+- 3 epochs, effective batch 8 (1×8 accum), lr 1e-4 cosine, warmup 5%, seq 1536, seed 42
+- Prompt-masked loss (labels −100 on system+user context; loss only on target JSON)
+- Single RTX 3090 24GB slot; runs alongside resident Ollama (no eviction; ~12GB/GPU free)
+
+## Eval: tool-call validity & stall rate (held-out chats)
+
+Deterministic (greedy) generation, 512 new tokens, judged: `valid` = parses as JSON dict with all four keys, known tool name, dict tool_args; `invalid` = parses but violates shape; `stall` = no parseable JSON object.
+
+| model | validity | invalid | stall | n |
+|---|---|---|---|---|
+| Qwen2.5-7B-Instruct base | 1.7% (1) | 98.3% (58) | 0% (0) | 59 |
+| + this adapter | **84.7% (50)** | 0% (0) | 15.3% (9)* | 59 |
+
+*All 9 tuned stalls are 512-token-cap truncations in a single held-out chat with unusually long tool_args (valid JSON starts, cut mid-object) - harness cap, not model failure. Base emitted 58 near-miss JSONs (invalid) and only 1 fully valid call. Full protocol + per-record details in eval report / eval-*.json.
+
+## Usage
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+base = AutoModelForCausalLM.from_pretrained('Qwen/Qwen2.5-7B-Instruct', device_map='auto')
+model = PeftModel.from_pretrained(base, 'Alogotron/a0-toolcall-lora')
+# system prompt: instruct EXACTLY ONE JSON object with thoughts/headline/tool_name/tool_args
+```
+
+## Intended use & limits
+
+Use to harden small agent models against tool-call format stalls in Agent Zero-style loops. Trained on one agent household's conversations — tool distribution skews to code_execution (66%); JSON arguments generalize but niche tool semantics may not. Not a general-instruct tune.