Closed rhatdan closed 22 hours ago
This PR reverts a previous change that switched from llama-cli to llama-simple-chat. The implementation restores the original llama-cli command with its specific argument structure and command-line options.
sequenceDiagram
actor User
participant System
User->>System: Execute model
alt Using llama-cli
System->>System: Prepare exec_args with llama-cli
System->>System: Add --in-prefix, --in-suffix, --no-display-prompt
System->>System: Add prompt and common_params
opt GPU enabled
System->>System: Add GPU arguments
end
end
Note right of System: Reverted from llama-simple-chat to llama-cli
classDiagram
class Model {
-exec_args: List
-exec_model_path: String
+run(args)
}
note for Model "Reverted exec_args to use llama-cli with specific options"
class Args {
+container: bool
+debug: bool
+gpu: bool
+ARGS: List
}
Model --> Args : uses
note for Args "Arguments used to configure model execution"
Change | Details | Files |
---|---|---|
Reverted command-line interface from llama-simple-chat back to llama-cli |
|
ramalama/model.py |
Updated system test to match reverted CLI command |
|
test/system/030-run.bats |
The llama-simple-chat does not work properly yet.
This reverts commit 1db401da6efc052185b23e49c67b738a102c3998.
Summary by Sourcery
Revert the integration of 'llama-simple-chat' and restore 'llama-cli' as the command-line interface for executing models due to unresolved issues with 'llama-simple-chat'. Update the system test to align with this change.
Enhancements:
Tests: