Create model.yml

model.yml

@@ -0,0 +1,20 @@
+name: tinyllama
+model: tinyllama:1B
+version: 1
+
+files:
+  - llama_model_path: model.gguf
+
+# Results Preferences
+top_p: 0.95
+temperature: 0.7
+frequency_penalty: 0
+presence_penalty: 0
+max_tokens: 4096 # Infer from base config.json -> max_position_embeddings
+stream: true # true | false
+
+# Engine / Model Settings
+ngl: 33 # Infer from base config.json -> num_attention_heads
+ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
+engine: cortex.llamacpp
+prompt_template: "<|system|>\n{system_message}<|user|>\n{prompt}<|assistant|>"