mirror of
https://github.com/ollama/ollama.git
synced 2026-10-21 19:11:17 +00:00
16b4376aea
* bench: use code prompts for prompt-token runs Replace the synthetic word-list prompt with packed HumanEval Python prompts so speculative draft models see code-like continuations. Keep the benchmark on the chat path, and calibrate -prompt-tokens with untimed chat probes that read PromptEvalCount instead of relying on a separate token-count API. Each request still gets a nonce prefix to avoid prefix-cache hits while timed epochs measure the chat-rendered workload. * review comments * use different windows for each epoch * add OpenAI API support * address comments |
||
|---|---|---|
| .. | ||
| bench | ||
| config | ||
| internal/fileutil | ||
| launch | ||
| tui | ||
| cloud_suggest.go | ||
| cloud_suggest_test.go | ||
| cmd.go | ||
| cmd_launcher_test.go | ||
| cmd_test.go | ||
| create_safetensors.go | ||
| create_safetensors_remote.go | ||
| create_safetensors_remote_test.go | ||
| create_safetensors_test.go | ||
| editor_unix.go | ||
| editor_windows.go | ||
| interactive.go | ||
| interactive_test.go | ||
| start.go | ||
| start_darwin.go | ||
| start_default.go | ||
| start_windows.go | ||
| warn_thinking_test.go | ||
| welcome.go | ||
| welcome_test.go | ||