ThoxEdge-RustCoder-0.5B

Rust Completion Model — a Rust-leaning fine-tune trained by THOX.ai on a public Apache-2.0 Rust code corpus (74,606 filtered code-producing examples): a LoRA fine-tune (rank 32), merged into the base weights

MultiPL-E HumanEval-Rust: 28.21% chat mode vs 25.64% base (156 problems, executed) · 0.5B fine-tune · Safetensors + GGUF in repo

Your AI. Your Data. Your Rules.™

Status: PUBLISHED. A Rust-leaning fine-tune trained by THOX on a public Apache-2.0 Rust code corpus (74,606 filtered code-producing examples): a rank-32 LoRA fine-tune, merged into the base weights. MultiPL-E HumanEval-Rust measured at 28.21% chat mode vs 25.64% base (156 problems, executed) — full results under Evaluation. See Files for exactly what this repo contains.

Summary

ThoxEdge-RustCoder-0.5B is a Rust-leaning fine-tune trained by THOX.ai on a public Apache-2.0 Rust code corpus (74,606 filtered code-producing examples): a LoRA fine-tune (rank 32), merged into the base weights. It serves cheap Rust completion in ThoxRoute's lowest tier. It is a 0.5B model and is not a strong Rust coder; the numbers below are a same-harness delta measurement, nothing more. It is a hosted/desktop model: its GGUF ladder spans only about 260 MB because a large share of its parameters sit in an embedding that does not quantize down, so it does not fit THOX's smallest devices.

Highlights

• THOX fine-tune: a LoRA fine-tune (rank 32), merged into the base weights.
• This repo ships safetensors only (no GGUF): bash hf download Thox-ai/ThoxEdge-RustCoder-0.5B --local-dir ./ThoxEdge-RustCoder-0.5B

Specifications

Files

Run it

This repo ships safetensors only (no GGUF):

hf download Thox-ai/ThoxEdge-RustCoder-0.5B --local-dir ./ThoxEdge-RustCoder-0.5B

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Thox-ai/ThoxEdge-RustCoder-0.5B")
model = AutoModelForCausalLM.from_pretrained("Thox-ai/ThoxEdge-RustCoder-0.5B")

Prompting matters. Ask for a complete function body in plain terms, for example "Write the complete body of the Rust function below." Do not prompt with "Complete the Rust code. Output only the missing code." — that phrasing matches training rows whose targets are short fragments, and this checkpoint answers it with a fragment (measured 2.56% where the recommended wording scores 28.21%).

Platforms

Intended use

• Cheap Rust code completion on hosts, inside the THOX stack.
• Out of scope: medical, legal, financial, safety-critical, or other high-stakes decisions without human review; unattended control of physical devices without a confirmation step.

Training data and procedure

THOX fine-tune of Qwen/Qwen2.5-Coder-0.5B-Instruct. The corpus and procedure are described in this card as published at release (see Summary and Evaluation); no training beyond what this card describes is claimed for this repository.

Evaluation

MultiPL-E HumanEval-Rust, 156 problems, executed (each generation is compiled and its assertions run), greedy decoding, both models scored in the same job:

The noise floor of this harness is about ±1 problem (±0.64 pp); both deltas clear it, and anything under about 1.5 pp should be treated as a tie. Assembly is deliberately generous (a body-only or whole-function answer passes if either works), so these numbers are not comparable to published MultiPL-E leaderboards; the delta between the rows is the measurement. No THOX GATE49 result is published for this model.

Limitations

• It fails roughly seven of every ten HumanEval-Rust problems (28.21% pass@1 in its best mode).
• A training-renderer defect placed auxiliary output fields inside the code fence in about half the rows of three training categories; it caused no measured regression, and this checkpoint retains the prompt sensitivity described above.
• Not sized for THOX's smallest devices (see summary).

License

Apache-2.0. The THOX fine-tune and additions in this repo are covered under Apache-2.0; the training corpus is also Apache-2.0. See the license text for terms.

THOX.ai — Your AI. Your Data. Your Rules.™

Provenance

Published by THOX.ai as Thox-ai/ThoxEdge-RustCoder-0.5B. Upstream base: Qwen/Qwen2.5-Coder-0.5B-Instruct. This card was conformed to THOX Model Card Standard v1.0 on 2026-10-31 (frontmatter, tags, header, files, and section structure); the technical content is as published at release.

Citation

@misc{thoxai2026thoxedgerustcoder05b,
      title={ThoxEdge-RustCoder-0.5B},
      author={THOX.ai},
      year={2026},
      url={https://huggingface.co/Thox-ai/ThoxEdge-RustCoder-0.5B}
}