diff options
Diffstat (limited to 'llama.cpp/examples/speculative-simple/README.md')
| -rw-r--r-- | llama.cpp/examples/speculative-simple/README.md | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/llama.cpp/examples/speculative-simple/README.md b/llama.cpp/examples/speculative-simple/README.md new file mode 100644 index 0000000..e3a6c6b --- /dev/null +++ b/llama.cpp/examples/speculative-simple/README.md @@ -0,0 +1,12 @@ +# llama.cpp/examples/speculative-simple + +Demonstration of basic greedy speculative decoding + +```bash +./bin/llama-speculative-simple \ + -m ../models/qwen2.5-32b-coder-instruct/ggml-model-q8_0.gguf \ + -md ../models/qwen2.5-1.5b-coder-instruct/ggml-model-q4_0.gguf \ + -f test.txt -c 0 -ngl 99 --color \ + --sampling-seq k --top-k 1 -fa --temp 0.0 \ + -ngld 99 --draft-max 16 --draft-min 5 --draft-p-min 0.9 +``` |