diff options
Diffstat (limited to 'examples/perplexity')
| -rw-r--r-- | examples/perplexity/perplexity.cpp | 35 |
1 files changed, 5 insertions, 30 deletions
diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp index d474bc50..299a1999 100644 --- a/examples/perplexity/perplexity.cpp +++ b/examples/perplexity/perplexity.cpp @@ -122,36 +122,11 @@ int main(int argc, char ** argv) { llama_context * ctx; - // load the model - { - auto lparams = llama_context_default_params(); - - lparams.n_ctx = params.n_ctx; - lparams.n_parts = params.n_parts; - lparams.seed = params.seed; - lparams.f16_kv = params.memory_f16; - lparams.logits_all = params.perplexity; - lparams.use_mmap = params.use_mmap; - lparams.use_mlock = params.use_mlock; - lparams.embedding = params.embedding; - - ctx = llama_init_from_file(params.model.c_str(), lparams); - - if (ctx == NULL) { - fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str()); - return 1; - } - } - - if (!params.lora_adapter.empty()) { - int err = llama_apply_lora_from_file(ctx, - params.lora_adapter.c_str(), - params.lora_base.empty() ? NULL : params.lora_base.c_str(), - params.n_threads); - if (err != 0) { - fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__); - return 1; - } + // load the model and apply lora adapter, if any + ctx = llama_init_from_gpt_params(params); + if (ctx == NULL) { + fprintf(stderr, "%s: error: unable to load model\n", __func__); + return 1; } // print system information |