fullstack commited on
Commit
63c0baf
1 Parent(s): 1a821d0

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. run_vllm_2b.sh +2 -2
run_vllm_2b.sh CHANGED
@@ -6,6 +6,6 @@ VLLM_ALLOW_RUNTIME_LORA_UPDATING=1 VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve ~/
6
  --max-model-len 8192 \
7
  --disable-log-requests \
8
  --enable-lora \
9
- --lora-modules gpqa=./gpqa \
10
 
11
- # --guided-decoding-backend lm-format-enforcer \
 
6
  --max-model-len 8192 \
7
  --disable-log-requests \
8
  --enable-lora \
9
+ --lora-modules gpqa=./ \
10
 
11
+ # --guided-decoding-backend lm-format-enforcer \