A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
README: short Filesystem model section above CHIP-8 (code on rv-store); Quickstarts install the hf extra (torch, transformers)
Divyansh Agrawal26a0a6904ff6
diff --git a/README.md b/README.mdindex 025a5f1..9b2c464 100644--- a/README.md+++ b/README.md@@ -43,7 +43,7 @@ base: KL 6e-4, against a noise floor of 5e-4.## Quickstart```bash-git clone https://github.com/divagr18/qwenputer && cd qwenputer/experimental/riscv && uv sync+git clone https://github.com/divagr18/qwenputer && cd qwenputer/experimental/riscv && uv sync --extra hfhf download divagr1925/Qwen3.5-4B-Qwenputer --local-dir qwenputer-rvuv run python -m chipformer.rv.chat qwenputer-rv --firmware tests/data/rv/calc-bridge.elf \--ask "Use the calc tool: what is 123456789 * 987654321?"@@ -77,6 +77,23 @@ token names the row, the `VAL` token after it carries the value, and `STEP` endsNothing here needed a new layer type: the computer's memory is the same Gated DeltaNetrecurrence Qwen3.5 already uses for language.+## The Filesystem model++[`divagr1925/Qwen3.5-4B-Qwenputer-Filesystem`](https://huggingface.co/divagr1925/Qwen3.5-4B-Qwenputer-Filesystem)++This is the same RISC-V model with a filesystem added to its DeltaNet state. Qwen gets five more+tools, `put`, `append`, `get`, `list` and `delete`, and the compiled layers answer them the same+way they answer `calc`. It holds up to 512 files, about 53,000 tokens of text. Save the state at+the end of a conversation and the files are still there in the next one.++| Benchmark | Base Qwen3.5-4B | **Qwenputer Filesystem** | Python tool (host) |+|---|---|---|---|+| Multi-session recall, 90 questions | 7.8 | **83.3** | 78.9 |+| Facts that changed in a later session, 30 questions | 3.3 | **90.0** | 83.3 |++Its code is on the [`rv-store`](https://github.com/divagr18/qwenputer/tree/rv-store/experimental/riscv)+branch for now. The model card has the quickstart and the full results.+## The CHIP-8 model[`divagr1925/Qwen3.5-4B-Qwenputer-CHIP8`](https://huggingface.co/divagr1925/Qwen3.5-4B-Qwenputer-CHIP8)@@ -169,7 +186,7 @@ then reads the printed answer like ordinary text.```bashgit clone https://github.com/divagr18/qwenputer && cd qwenputer-uv sync+uv sync --extra hfhf download divagr1925/Qwen3.5-4B-Qwenputer-CHIP8 --local-dir qwenputer-4buv run python -m chipformer.q35.demo qwenputer-4b # Qwen uses its tool-call syntaxdiff --git a/experimental/riscv/README.md b/experimental/riscv/README.mdindex 0a17455..54e1a8f 100644--- a/experimental/riscv/README.md+++ b/experimental/riscv/README.md@@ -28,5 +28,5 @@ an L4, and in generation it runs at about 3,200 trace tokens a second.[`docs/rv32-p3-status.md`](docs/rv32-p3-status.md) has the in-Qwen status.```bash-cd experimental/riscv && uv sync && uv run pytest tests -q+cd experimental/riscv && uv sync --extra hf && uv run pytest tests -q```