From 0e89203b517c95ec6675eda75d200a60d1e8921d Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Wed, 18 Oct 2023 16:21:57 +0300 Subject: speculative : add tree-based sampling example (#3624) * sampling : one sequence per sampling context ggml-ci * speculative : add tree-based sampling support ggml-ci * speculative : reuse the n_parallel CLI param * speculative : refactor sampling * examples : fix build after sampling refactoring ggml-ci * batched : fix n_seq_id * sampling : fix malloc ggml-ci * swift : fix build ggml-ci * swift : try to fix build ggml-ci * prompts : add assistant.txt * common : add llama_batch_add() and llama_batch_clear() helpers * speculative : minor refactor ggml-ci * minor : comments + rename ggml-ci * speculative : fix off-by-one for n_drafted * speculative : fix the n_drafted fix + p constants --- examples/llava/llava.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/llava/llava.cpp') diff --git a/examples/llava/llava.cpp b/examples/llava/llava.cpp index b24cb2e6..f0974d5b 100644 --- a/examples/llava/llava.cpp +++ b/examples/llava/llava.cpp @@ -127,7 +127,7 @@ int main(int argc, char ** argv) { const int max_tgt_len = params.n_predict < 0 ? 256 : params.n_predict; - eval_string(ctx_llama, "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER:", params.n_batch, &n_past, true); + eval_string(ctx_llama, "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER:", params.n_batch, &n_past, true); eval_image_embd(ctx_llama, image_embd, n_img_pos, params.n_batch, &n_past); eval_string(ctx_llama, (params.prompt + "\nASSISTANT:").c_str(), params.n_batch, &n_past, false); -- cgit v1.2.3