A tiny, randomly-initialised Llama pair for exercising subfolder loading of a speculative draft model. It exists so inference engines can test the code path in CI without downloading a real checkpoint.

.              <- target model, 2 layers, ~4M params
└── DFlash/    <- draft model,  1 layer,  ~4M params

Both share the same tokenizer and vocabulary, so the draft is a valid speculator for the target.

A Hugging Face repo id may contain at most one /, so org/repo/DFlash is not a valid id and cannot be passed as a single string. A draft bundled inside its target's repository therefore has to be addressed as a repo id plus a separate sub-path, which most engines have no parameter for.

This matters in practice: shipping a draft inside its target repo keeps the pair versioned together and downloadable in one fetch, rather than as two repos that can drift apart.

Engines adding support should accept the draft as (model="poolside/spec-decoding-subfolder-fixture", subfolder="DFlash").

Built with transformers from LlamaConfig (hidden 64, intermediate 128, 4 heads, tied embeddings), torch.manual_seed(0). Tokenizer copied from hf-internal-testing/llama-tokenizer. No trained parameters, no proprietary data.