|
Download examples/speculative-simple/README.md from OpenTransformer/llama.cpp-prismml: direct link, hf CLI and curl.
- Browser
- Download file 422 Bytes
-
https://huggingface.co/OpenTransformer/llama.cpp-prismml/resolve/main/examples/speculative-simple/README.md
- Command line
-
hf download hf://OpenTransformer/llama.cpp-prismml/examples/speculative-simple/README.md
-
curl -L -o README.md https://huggingface.co/OpenTransformer/llama.cpp-prismml/resolve/main/examples/speculative-simple/README.md
422 Bytes
llama.cpp/examples/speculative-simple
Demonstration of basic greedy speculative decoding
./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