diff --git a/Makefile b/Makefile index ade38042f0e1..78361f06162b 100644 --- a/Makefile +++ b/Makefile @@ -5,7 +5,7 @@ BINARY_NAME=local-ai # llama.cpp versions GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be -CPPLLAMA_VERSION?=37e7854c104301c5b5323ccc40e07699f3a62c3e +CPPLLAMA_VERSION?=c50a82ce0f71558cbb8e555146ba124251504b38 # gpt4all version GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all diff --git a/aio/cpu/text-to-text.yaml b/aio/cpu/text-to-text.yaml index aeb3c842680d..d30f403edc00 100644 --- a/aio/cpu/text-to-text.yaml +++ b/aio/cpu/text-to-text.yaml @@ -41,6 +41,7 @@ f16: true stopwords: - <|im_end|> - +- "\n" usage: | curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "gpt-4", diff --git a/aio/gpu-8g/text-to-text.yaml b/aio/gpu-8g/text-to-text.yaml index 1a67169b6854..1645a2573852 100644 --- a/aio/gpu-8g/text-to-text.yaml +++ b/aio/gpu-8g/text-to-text.yaml @@ -41,6 +41,7 @@ f16: true stopwords: - <|im_end|> - +- "\n" usage: | curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "gpt-4", diff --git a/aio/intel/text-to-text.yaml b/aio/intel/text-to-text.yaml index 0577d19b164a..3f3d2c39cb9a 100644 --- a/aio/intel/text-to-text.yaml +++ b/aio/intel/text-to-text.yaml @@ -40,6 +40,7 @@ template: context_size: 4096 stopwords: - <|im_end|> +- "\n" - usage: | curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ diff --git a/embedded/models/hermes-2-pro-mistral.yaml b/embedded/models/hermes-2-pro-mistral.yaml index 108216f5c39b..3792be78bfa2 100644 --- a/embedded/models/hermes-2-pro-mistral.yaml +++ b/embedded/models/hermes-2-pro-mistral.yaml @@ -41,6 +41,7 @@ f16: true stopwords: - <|im_end|> - +- "\n" usage: | curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "hermes-2-pro-mistral",