vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Updating run-with-preset.py to use new binary names.

Browse source 
Updating docs around `perplexity` binary rename.
This commit is contained in:
HanClinto 2024-06-10 15:23:32 -07:00
parent 2fd66b2ce2
commit 72660c357c
2 changed files with 9 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/perplexity/perplexity.cpp
View file

@ -476,7 +476,7 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
}
// Download: https://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.zip
// Run `./perplexity -m models/7B/ggml-model-q4_0.bin -f wiki.test.raw`
// Run `./llama-perplexity -m models/7B/ggml-model-q4_0.bin -f wiki.test.raw`
// Output: `perplexity: 13.5106 [114/114]`
// BOS tokens will be added for each chunk before eval

16
scripts/run-with-preset.py
View file

@ -10,7 +10,7 @@ import yaml
logger = logging.getLogger("run-with-preset")
CLI_ARGS_MAIN_PERPLEXITY = [
CLI_ARGS_LLAMA_CLI_PERPLEXITY = [
"batch-size", "cfg-negative-prompt", "cfg-scale", "chunks", "color", "ctx-size", "escape",
"export", "file", "frequency-penalty", "grammar", "grammar-file", "hellaswag",
"hellaswag-tasks", "ignore-eos", "in-prefix", "in-prefix-bos", "in-suffix",
@ -29,7 +29,7 @@ CLI_ARGS_LLAMA_BENCH = [
"n-prompt", "output", "repetitions", "tensor-split", "threads", "verbose"
]
CLI_ARGS_SERVER = [
CLI_ARGS_LLAMA_SERVER = [
"alias", "batch-size", "ctx-size", "embedding", "host", "memory-f32", "lora", "lora-base",
"low-vram", "main-gpu", "mlock", "model", "n-gpu-layers", "n-probs", "no-mmap", "no-mul-mat-q",
"numa", "path", "port", "rope-freq-base", "timeout", "rope-freq-scale", "tensor-split",
@ -37,7 +37,7 @@ CLI_ARGS_SERVER = [
]
description = """Run llama.cpp binaries with presets from YAML file(s).
To specify which binary should be run, specify the "binary" property (main, perplexity, llama-bench, and server are supported).
To specify which binary should be run, specify the "binary" property (llama-cli, llama-perplexity, llama-bench, and llama-server are supported).
To get a preset file template, run a llama.cpp binary with the "--logdir" CLI argument.
Formatting considerations:
@ -77,19 +77,19 @@ for yaml_file in known_args.yaml_files:
props = {prop.replace("_", "-"): val for prop, val in props.items()}
binary = props.pop("binary", "main")
binary = props.pop("binary", "llama-cli")
if known_args.binary:
binary = known_args.binary
if os.path.exists(f"./{binary}"):
binary = f"./{binary}"
if binary.lower().endswith("main") or binary.lower().endswith("perplexity"):
cli_args = CLI_ARGS_MAIN_PERPLEXITY
if binary.lower().endswith("llama-cli") or binary.lower().endswith("llama-perplexity"):
cli_args = CLI_ARGS_LLAMA_CLI_PERPLEXITY
elif binary.lower().endswith("llama-bench"):
cli_args = CLI_ARGS_LLAMA_BENCH
elif binary.lower().endswith("server"):
cli_args = CLI_ARGS_SERVER
elif binary.lower().endswith("llama-server"):
cli_args = CLI_ARGS_LLAMA_SERVER
else:
logger.error(f"Unknown binary: {binary}")
sys.exit(1)