init model gemma 2 2b

model.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd87fc03fe3d651ac419ae35f4a0e6d861167db156572b6c4b90fb81822a3547
-size 5127231648
+oid sha256:af92b6a034fd095807bd339ae9268ceba1a951201994063d5eea15e564f0a42f
+size 1708582496

model.yml

@@ -1,5 +1,5 @@
-name: gemma
-model: gemma:7B
+name: gemma2
+model: gemma2:2B
 version: 1
 
 # Results Preferences
@@ -14,7 +14,7 @@ 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
+ngl: 300 # Infer from base config.json -> num_attention_heads
 ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
 engine: cortex.llamacpp
 prompt_template: "<start_of_turn>user\n{prompt}<end_of_turn>\n<start_of_turn>model"