fix fc integration

arch/config_generator.py

@@ -4,7 +4,7 @@
 from jsonschema import validate
 
 ENVOY_CONFIG_TEMPLATE_FILE = os.getenv('ENVOY_CONFIG_TEMPLATE_FILE', 'envoy.template.yaml')
-ARCH_CONFIG_FILE = os.getenv('ARCH_CONFIG_FILE', '/root/arch_config.yaml')
+ARCH_CONFIG_FILE = os.getenv('ARCH_CONFIG_FILE', '/config/arch_config.yaml')
 ENVOY_CONFIG_FILE_RENDERED = os.getenv('ENVOY_CONFIG_FILE_RENDERED', '/etc/envoy/envoy.yaml')
 ARCH_CONFIG_SCHEMA_FILE = os.getenv('ARCH_CONFIG_SCHEMA_FILE', 'arch_config_schema.yaml')
 

demos/function_calling/.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Arch-Function-Calling-1.5B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Function-Calling-1.5B.gguf filter=lfs diff=lfs merge=lfs -text

demos/function_calling/docker-compose.yaml

@@ -42,7 +42,7 @@ services:
     << : *common-vars
     environment:
       - OLLAMA_ENDPOINT=${OLLAMA_ENDPOINT:-host.docker.internal}
-      - FC_URL=${FC_URL:-empty}
+      - FC_URL=${FC_URL:-https://arch-fc-free-trial-4mzywewe.uc.gateway.dev/v1}
       - OLLAMA_MODEL=Arch-Function-Calling-3B-Q4_K_M
       - MODE=${MODE:-cloud}
       # uncomment following line to use ollama endpoint that is hosted by docker

model_server/openai_params.yaml

@@ -1,8 +1,7 @@
 params:
-  temperature: 0.0001
+  temperature: 0.01
   top_p : 0.5
   repetition_penalty: 1.0
   top_k: 50
-  max_tokens: 128
-  stop: ["<|im_start|>", "<|im_end|>"]
+  max_tokens: 512
   stop_token_ids: [151645, 151643]