Add C2Rust model card

Document the model, companion benchmark, setup, intended use, limitations, and licensing.

README.md

@@ -0,0 +1,116 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen3.5-27B
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- code
+- c
+- rust
+- code-translation
+- c-to-rust
+- qwen3.5
+---
+
+# C2Rust
+
+C2Rust is a 27B-parameter BF16 Qwen3.5 checkpoint for translating C programs into behaviorally
+equivalent Rust. It is released alongside an execution-based benchmark that compiles each generated
+translation and checks its output against the reference C program.
+
+## Resources
+
+- [Benchmark, evaluation harness, and setup instructions](https://github.com/moxin-org/C2Rust)
+- [Base model: Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B)
+- [SACTOR translation engine](https://github.com/qsdrqs/sactor)
+
+## Model details
+
+| Field | Value |
+|---|---|
+| Base model | `Qwen/Qwen3.5-27B` |
+| Architecture | Qwen3.5 causal language model with vision encoder |
+| Parameters | 27B |
+| Weight format | Safetensors |
+| Precision | BF16 |
+| Primary task | C→Rust program translation |
+
+## Intended use
+
+The model is intended for research and experimentation on C→Rust translation. Its output should be
+treated as a candidate translation: compile it, test it against the original program, and review it
+for correctness, safety, and maintainability before use.
+
+The companion benchmark evaluates a single translation stage that preserves the C interface and may
+produce `unsafe` Rust. It does not establish that generated code is memory-safe, idiomatic, secure,
+or suitable for production.
+
+## Running the model with the benchmark
+
+Download the checkpoint:
+
+```bash
+hf download moxin-org/C2Rust --local-dir /path/to/C2Rust-model
+```
+
+Clone and prepare the benchmark:
+
+```bash
+git clone https://github.com/moxin-org/C2Rust.git
+cd C2Rust
+bash fix_paths.sh
+
+cd engine
+uv sync
+./update_rust_ast_parser.sh
+cargo build --release
+cd ..
+```
+
+Create an SGLang environment, point `SERVE_VENV` at it, and launch the checkpoint. The helper script
+sets the serving options expected by the benchmark:
+
+```bash
+export SERVE_VENV=/path/to/sglang-venv
+./scripts/launch_model.sh /path/to/C2Rust-model 0,1 30878 2
+```
+
+In another shell, run a two-problem smoke test before a full evaluation:
+
+```bash
+python3 scripts/run_eval.py configs/native_prompt.toml results/_smoke \
+  --modes argv --limit 2 --workers 1
+```
+
+See the [benchmark README](https://github.com/moxin-org/C2Rust#setup-once-per-machine) and
+[`SETUP.md`](https://github.com/moxin-org/C2Rust/blob/main/SETUP.md) for system dependencies,
+multi-seed evaluation, aggregation, and troubleshooting.
+
+## Evaluation protocol
+
+The companion CodeNet benchmark contains 200 C programs: 92 use command-line arguments and 108 use
+standard input. A problem passes only when the generated Rust program compiles and matches the
+reference C program on every test case. Decoding is fixed at temperature 0.6, top-p 0.95, and top-k
+20. Because individual runs are noisy, the repository reports five-seed means with standard
+deviation and a bootstrap confidence interval.
+
+No reference model score is claimed in the benchmark repository. Use its shipped configuration and
+five-seed aggregation script for comparable measurements.
+
+## Limitations
+
+- Generated translations may fail to compile or may differ from the source program on untested
+  inputs.
+- Passing the supplied tests is not a proof of semantic equivalence, memory safety, or security.
+- The benchmark's primary flow permits `unsafe` Rust and prioritizes behavioral preservation over
+  idiomatic Rust.
+- Training-data and training-procedure details are not included in the current release.
+
+## Licenses and attribution
+
+The checkpoint is released under Apache-2.0 and is based on
+[Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B). The benchmark repository is
+Apache-2.0. Its dataset includes material derived from IBM Project CodeNet under
+CDLA-Permissive-2.0; see the benchmark's
+[dataset provenance and terms](https://github.com/moxin-org/C2Rust/blob/main/CodeNet/README.md).