py-llama predictor

doc/oi-notes.md

@@ -0,0 +1,47 @@
+
+
+
+ interpreter --api_base http://192.168.0.11:11434/v1/
+
+interpreter --model "gpt-3.5-turbo" # mistral
+interpreter --model "mistral" --api_base http://192.168.0.11:11434/v1/
+
+        Mac/Linux: 'export OPENAI_API_KEY=your-key-here',
+        Windows: 'setx OPENAI_API_KEY your-key-here' then restart terminal.
+interpreter --local
+
+interpreter --api_base http://192.168.0.11:11434/v1 --api_key "" --model openai/local
+
+
+
+interpreter --api_base http://192.168.0.137:1234/v1 --api_key "" --model openai/local
+192.168.0.137
+
+
+# Load a model, start the server, and run this example in your terminal
+# Choose between streaming and non-streaming mode by setting the "stream" field
+
+curl http://192.168.0.11:11434/v1/chat/completions \
+-H "Content-Type: application/json" \
+-d '{ 
+  "messages": [ 
+    { "role": "system", "content": "Always answer in rhymes." },
+    { "role": "user", "content": "Introduce yourself." }
+  ], 
+  "temperature": 0.7, 
+  "max_tokens": -1,
+  "stream": false
+}'
+
+
+curl http://192.168.0.137:1234/v1/chat/completions \
+-H "Content-Type: application/json" \
+-d '{ 
+  "messages": [ 
+    { "role": "system", "content": "Always answer in rhymes." },
+    { "role": "user", "content": "Introduce yourself." }
+  ], 
+  "temperature": 0.7, 
+  "max_tokens": -1,
+  "stream": false
+}'