Download Makefile from harshithsaiv/kv-cache-compression: direct link, hf CLI and curl.
- Browser
- Download file 898 Bytes
-
https://huggingface.co/harshithsaiv/kv-cache-compression/resolve/598ef5913978525b33dd525b9a0ab3b369e723bf/Makefile
- Command line
-
hf download hf://harshithsaiv/kv-cache-compression@598ef5913978525b33dd525b9a0ab3b369e723bf/Makefile
-
curl -L -o Makefile https://huggingface.co/harshithsaiv/kv-cache-compression/resolve/598ef5913978525b33dd525b9a0ab3b369e723bf/Makefile
898 Bytes
| MODEL ?= mistral-7b | |
| install: | |
| pip install -r requirements.txt | |
| baseline: | |
| python3 scripts/baseline.py $(MODEL) | |
| calibrate: | |
| python3 scripts/calibrate.py $(MODEL) | |
| integrate: | |
| python3 scripts/integrate.py $(MODEL) | |
| benchmark: | |
| python3 scripts/benchmark.py $(MODEL) | |
| benchmark-long: | |
| python3 scripts/benchmark_long_context.py $(MODEL) | |
| visualize: | |
| python3 scripts/visualize_results.py | |
| python3 scripts/visualize_long_context.py | |
| python3 scripts/visualize_sensitivity.py | |
| run-all: | |
| make baseline MODEL=$(MODEL) | |
| make calibrate MODEL=$(MODEL) | |
| make integrate MODEL=$(MODEL) | |
| make benchmark MODEL=$(MODEL) | |
| make visualize | |
| run-mistral: | |
| make run-all MODEL=mistral-7b | |
| run-llama: | |
| make run-all MODEL=llama-3-8b | |
| run-both: | |
| make run-all MODEL=mistral-7b | |
| make run-all MODEL=llama-3-8b | |
| .PHONY: install baseline calibrate integrate benchmark benchmark-long visualize run-all run-mistral run-llama run-both |