llama_sample_classifier_free_guidance method
void
llama_sample_classifier_free_guidance(
- Pointer<
llama_context> ctx, - Pointer<
llama_token_data_array> candidates, - Pointer<
llama_context> guidance_ctx, - double scale,
@details Apply classifier-free guidance to the logits as described in academic paper "Stay on topic with Classifier-Free Guidance" https://arxiv.org/abs/2306.17806
@param candidates A vector of llama_token_data
containing the candidate tokens, the logits must be directly extracted from the original generation context without being sorted.
@params guidance_ctx A separate context from the same model. Other than a negative prompt at the beginning, it should have all generated and user input tokens copied from the main context.
@params scale Guidance strength. 1.0f means no guidance. Higher values mean stronger guidance.
Implementation
void llama_sample_classifier_free_guidance(
ffi.Pointer<llama_context> ctx,
ffi.Pointer<llama_token_data_array> candidates,
ffi.Pointer<llama_context> guidance_ctx,
double scale,
) {
return _llama_sample_classifier_free_guidance(
ctx,
candidates,
guidance_ctx,
scale,
);
}