Download run_gemma2-2b.sh from forcemultiplier/instruct-evolve-xml-gem2b-adapter: direct link, hf CLI and curl.
- Browser
- Download file 343 Bytes
-
https://huggingface.co/forcemultiplier/instruct-evolve-xml-gem2b-adapter/resolve/main/run_gemma2-2b.sh
- Command line
-
hf download hf://forcemultiplier/instruct-evolve-xml-gem2b-adapter/run_gemma2-2b.sh
-
curl -L -o run_gemma2-2b.sh https://huggingface.co/forcemultiplier/instruct-evolve-xml-gem2b-adapter/resolve/main/run_gemma2-2b.sh
343 Bytes
| VLLM_ALLOW_RUNTIME_LORA_UPDATING=1 VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve ~/models/gemma2-2b \ | |
| --gpu-memory-utilization=1 \ | |
| --port 6002 \ | |
| --served-model-name="gemma" \ | |
| --trust-remote-code \ | |
| --max-model-len 8192 \ | |
| --disable-log-requests \ | |
| --enable-lora \ | |
| --lora-modules lora=./output/unsloth/lora_model --max-lora-rank 64 | |