ducklm/config/models.yaml

74 lines
1.8 KiB
YAML

default_provider: llama_server
models:
thinker:
provider: llama_server
base_url: http://127.0.0.1:8081/v1
model: local-main
purpose: free_cognition
structured_output: false
temperature: 0.4
max_output_tokens: 8192
system_prompt: prompts/roles/thinker.md
critic:
provider: llama_server
base_url: http://127.0.0.1:8081/v1
model: local-main
purpose: reflection
structured_output: false
temperature: 0.1
max_output_tokens: 4096
system_prompt: prompts/roles/critic.md
coder:
provider: llama_server
base_url: http://127.0.0.1:8081/v1
model: local-main
purpose: code_generation
structured_output: false
temperature: 0.2
max_output_tokens: 16384
system_prompt: prompts/roles/coder.md
action:
provider: llama_server
base_url: http://127.0.0.1:8081/v1
model: local-main
purpose: action_directive
structured_output: true
temperature: 0.0
max_output_tokens: 2048
system_prompt: prompts/roles/action.md
response_schema: duck_core/schemas/action_directive.schema.json
summary:
provider: llama_server
base_url: http://127.0.0.1:8081/v1
model: local-main
purpose: context_summary
structured_output: false
temperature: 0.1
max_output_tokens: 4096
system_prompt: prompts/roles/summary.md
memory_policy:
provider: llama_server
base_url: http://127.0.0.1:8081/v1
model: local-main
purpose: memory_classification
structured_output: true
temperature: 0.1
max_output_tokens: 1024
system_prompt: prompts/roles/memory_policy.md
recall:
provider: llama_server
base_url: http://127.0.0.1:8081/v1
model: local-main
purpose: memory_recall
structured_output: true
temperature: 0.1
max_output_tokens: 2048
system_prompt: prompts/roles/recall.md