use separate hf cache dirs for chatgpt api integration test. its an unusual setup where we're running 2 exo instances on the same device which share a disk and hf cache

.circleci/config.yml

@@ -17,11 +17,11 @@ commands:
             source env/bin/activate
 
             # Start first instance
-            DEBUG_DISCOVERY=7 DEBUG=7 python3 main.py --inference-engine <<parameters.inference_engine>> --node-id "node1" --listen-port 5678 --broadcast-port 5679 --chatgpt-api-port 8000 --chatgpt-api-response-timeout-secs 900 > output1.log 2>&1 &
+            HF_HOME="$(pwd)/.hf_cache_node1" DEBUG_DISCOVERY=7 DEBUG=7 python3 main.py --inference-engine <<parameters.inference_engine>> --node-id "node1" --listen-port 5678 --broadcast-port 5679 --chatgpt-api-port 8000 --chatgpt-api-response-timeout-secs 900 > output1.log 2>&1 &
             PID1=$!
 
             # Start second instance
-            DEBUG_DISCOVERY=7 DEBUG=7 python3 main.py --inference-engine <<parameters.inference_engine>> --node-id "node2" --listen-port 5679 --broadcast-port 5678 --chatgpt-api-port 8001 --chatgpt-api-response-timeout-secs 900 > output2.log 2>&1 &
+            HF_HOME="$(pwd)/.hf_cache_node2" DEBUG_DISCOVERY=7 DEBUG=7 python3 main.py --inference-engine <<parameters.inference_engine>> --node-id "node2" --listen-port 5679 --broadcast-port 5678 --chatgpt-api-port 8001 --chatgpt-api-response-timeout-secs 900 > output2.log 2>&1 &
             PID2=$!
 
             # Wait for discovery