Temper-1-1.5B is Qwen2.5-Coder-1.5B-Instruct fine-tuned for writing Rust. On the standard HumanEval-Rust benchmark it solves 50.5% of tasks on the first try, more than Qwen2.5-Coder-3B at twice its size. The model was trained on the same 10 000 Rust examples as Temper-1-0.5B. Each example was written by DeepSeek-V4-Flash and passed the compiler and tests. This model had no reinforcement learning. HumanEval-Rust (multiple-rs from MultiPL-E, 156 tasks), %. pass@1 is the share of tasks solved on the first try, pass@10 the share solved in at least one of 10 tries. Every model ran through bigcode-evaluation-harness at commit 8fc5bae with the BigCode Models Leaderboard settings. The model completes code without a chat template, with temperature 0.2, top_p 0.95, 50 samples per task and 512 tokens including the prompt. Qwen2.5-Coder and StarCoder2 are the base versions. Qwen3.5-9B is the post-trained version. StarCoder2-3B scores 25.1 here and 24.5 on the leaderboard. The Temper-1-0.5B card reports HumanEval-RS with the task sent as a chat message, so its numbers there differ from this table. The default generation config samples with temperature 0.7, topp 0.8, topk 20 and repetition…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Языки программирования:
Rust
Задача: Генерация текста
Автор: maylore-ai
Теги: qwen2, rust, code, conversational, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 1,307
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
