| name: command-r | |
| model: command-r:35B | |
| 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: 131072 # 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: 131072 # Infer from base config.json -> max_position_embeddings | |
| engine: cortex.llamacpp | |
| prompt_template: "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" | |