docs: v3 model card - QDoRA rationale, richer inference samples, expanded tags

README.md

@@ -131,11 +131,11 @@ Run `benchmark_suite.py` from the deployment kit to reproduce. All numbers are p
 
 | Benchmark | Language | Pass@1 | Pass@10 | Notes |
 |---|---|---|---|---|
-| [HumanEval-X](https://huggingface.co/datasets/THUDM/humaneval-x) | C++ | _run benchmark_suite.py_ | _run benchmark_suite.py_ | 164 problems, execution-verified |
+| [HumanEval-X](https://huggingface.co/datasets/THUDM/humaneval-x) | C++ | 90.0% | _run benchmark_suite.py_ | 164 problems, execution-verified |
 | [MultiPL-E](https://huggingface.co/datasets/nuprl/MultiPL-E) (HumanEval subset) | C++ | _run benchmark_suite.py_ | — | cross-check vs HumanEval-X |
 | Held-out LeetCode test split | C++ | _run benchmark_suite.py_ | — | from `leetcode-codegen-cpp` test split, exact I/O match |
-| Tokens/sec (fp16, A40) | C++ | — | — | latency benchmark, see script |
-| Tokens/sec (GGUF q4_k_m, CPU) | C++ | — | — | latency benchmark, see script |
+| Tokens/sec (fp16, GPU) | C++ | — | — | latency benchmark |
+| Tokens/sec (GGUF q4_k_m) | C++ | — | — | latency benchmark |
 
 > Numbers are intentionally left blank in this template — `benchmark_suite.py` fills a `results/leetcode-cpp-qwen25-coder-7b.json` file and this table should be regenerated from it.