This commit is contained in:
Georgi Gerganov 2026-02-16 10:30:10 +02:00
parent cffd268bb3
commit 73e61d5b75
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
2 changed files with 5 additions and 5 deletions

View File

@ -14,7 +14,7 @@ Simple evaluation tool for llama.cpp with support for multiple datasets.
## Usage
```bash
python llama-eval-new.py \
python llama-eval.py \
--server http://127.0.0.1:8013 \
--model gpt-oss-20b-hf-low \
--judge-model gpt-oss-20b-hf-medium \

View File

@ -460,15 +460,15 @@ class Processor:
print(f"\nProcessing {n_cases} {self.dataset_type.upper()} questions...")
print(f"Server: {self.server_url} (model: {self.model_name})")
print(f"Threads: {self.threads}")
print(f"Max tokens: {self.n_predict}")
print(f"Seed: {self.seed}")
print(f"Sampling: temp={self.sampling_config.get('temperature', 'skip')}, top-k={self.sampling_config.get('top_k', 'skip')}, top-p={self.sampling_config.get('top_p', 'skip')}, min-p={self.sampling_config.get('min_p', 'skip')}")
print(f"Grader: {self.grader.grader_type}", end="")
if self.grader.grader_type == "llm":
judge_model = self.judge_model_name if self.judge_model_name else self.model_name
print(f" (judge server: {self.judge_server_url}, model: {judge_model})", end="")
print()
print(f"Threads: {self.threads}")
print(f"Max tokens: {self.n_predict}")
print(f"Seed: {self.seed}")
print(f"Sampling: temp={self.sampling_config.get('temperature', 'skip')}, top-k={self.sampling_config.get('top_k', 'skip')}, top-p={self.sampling_config.get('top_p', 'skip')}, min-p={self.sampling_config.get('min_p', 'skip')}")
print()
dataset_size = len(self.dataset.questions)