Slim fixture: mic-llama-slim

A 3.2M-parameter fixture for the llama MIC, covering HuggingFaceTB/SmolLM2-135M. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.

• Fixture key 449c36ea4c20. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
• Same architecture, smaller config: LlamaForCausalLM, shrunk by the generic rule in sweep.py (num_hidden_layers 2).
• Processor files copied byte for byte from HuggingFaceTB/SmolLM2-135M: generation_config.json, merges.txt, special_tokens_map.json, tokenizer.json, tokenizer_config.json, vocab.json.
• Random weights (seed 17). They passed the input-sensitivity gate: every perturbation of the contract's inputs moved the logits by at least 0.001 (weakest: input_ids:reverse, 2.12), so no training was needed.
• Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
• Saved in bfloat16, the dtype HuggingFaceTB/SmolLM2-135M loads in by default.
• Finite in float32, bfloat16, and float16 (forward, loss, gradients).

Built by build_fixtures.py; build.json records the pinned sources, gate results, and file hashes. The source repository commits only README.md and build.json; rebuild the other files with python example/build_fixtures.py --fixture mic-llama-slim.