Hugging Face's logo

cortexso
/
command-r

Text Generation
GGUF
cortex.cpp
Inference Endpoints
conversational
Model card Files Community
thuannh commited on
Commit
bfcbb7d
·
verified ·
1 Parent(s): b676b48

Update model.yml

Browse files
Files changed (1) hide show
  1. model.yml +1 -1
model.yml CHANGED
@@ -13,5 +13,5 @@ stream: true # true | false
13
  # Engine / Model Settings
14
  ngl: 33 # Infer from base config.json -> num_attention_heads
15
  ctx_len: 131072 # Infer from base config.json -> max_position_embeddings
16
- engine: cortex.llamacpp
17
  prompt_template: "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>"
 
13
  # Engine / Model Settings
14
  ngl: 33 # Infer from base config.json -> num_attention_heads
15
  ctx_len: 131072 # Infer from base config.json -> max_position_embeddings
16
+ engine: llama-cpp
17
  prompt_template: "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>"