Adding files for launching server and CLI but removing cluster specific stuff

examples/run_api_server_530B.sh

+#!/bin/bash
+DISTRIBUTED_ARGS="--nproc_per_node 16 \
+                  --nnodes 3 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+
+CHECKPOINT=<Path to checkpoint (e.g /gpt3-530b-megatron_tp16_pp3)>
+VOCAB_FILE=<Path to vocab.json (e.g. /gpt2-vocab.json)>
+MERGE_FILE=<Path to merges.txt (e.g. /gpt2-merges.txt)>
+
+pip install flask-restful
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS tools/run_api_server.py   /
+       --tensor-model-parallel-size 16  /
+       --pipeline-model-parallel-size 3  /
+       --num-layers 105  /
+       --hidden-size 20480  /
+       --load ${CHECKPOINT}  /
+       --num-attention-heads 128  /
+       --max-position-embeddings 2048  /
+       --tokenizer-type GPT2BPETokenizer  /
+       --fp16  /
+       --micro-batch-size 1  /
+       --seq-length 2048  /
+       --out-seq-length 2048  /
+       --temperature 1.0  /
+       --vocab-file $VOCAB_FILE  /
+       --merge-file $MERGE_FILE  /
+       --top_p 0.9  /
+	   --seed 42

examples/run_cli_530B.sh

+#!/bin/bash
+echo "Loading model and starting server.  May take several minutes"
+./run_api_server_530B.sh
+STATUS = 1
+while [ $STATUS -eq 1]
+do
+	sleep 20
+	curl -s -m 20 'http://localhost:5000/generate' -X 'PUT' -H 'Content-Type: application/json; charset=UTF-8'  -d '{"sentences":["Test2"], "max_len":30}' | head -n 1 | grep "HTTP/1.[01] [23].." > /dev/null
+	STATUS = $?
+done
+python tools/run_cli.py 'http://localhost:5000/generate' 

run_api_server_530B.sh

-#!/bin/bash
-CHECKPOINT="/home/universal-lm-data.cosmos549/scratch/jcasper/gpt3-530b-megatron_tp16_pp3"
-DATA_PATH="/home/universal-lm-data.cosmos549/scratch/mshoeybi/data/gpt2"
-VOCAB_FILE="${DATA_PATH}/bpe/gpt2-vocab.json"
-MERGE_FILE="${DATA_PATH}/bpe/gpt2-merges.txt"
-RUN_CMD=(
-python tools/run_api_server.py 
-       --tensor-model-parallel-size 16 
-       --pipeline-model-parallel-size 3 
-       --num-layers 105 
-       --hidden-size 20480 
-       --load ${CHECKPOINT} 
-       --num-attention-heads 128 
-       --max-position-embeddings 2048 
-       --tokenizer-type GPT2BPETokenizer 
-       --fp16 
-       --micro-batch-size 1 
-       --seq-length 2048 
-       --out-seq-length 2048 
-       --temperature 1.0 
-       --vocab-file $VOCAB_FILE 
-       --merge-file $MERGE_FILE 
-       --top_p 0.9 
-	   --seed 42
-)
-
-submit_job --duration 168 --nodes 3 --gpu 16 --reservation adlr-530b --partition batch_UN_dgx2_singlenode --mounts /home/universal-lm-data.cosmos549,/home/dcg-adlr-rprenger-source.cosmos352,/home/dcg-adlr-sgodil-data.cosmos233,/home/dcg-adlr-rprenger-output.cosmos349,/home/dcg-adlr-mchrzanowski-chidesign-data --image gitlab-master.nvidia.com/adlr/rprenger/megatron:latest --skip_ib_check --tasks_per_node 16 -c "${RUN_CMD[*]}"