From a31d00d904a7f762c0bd561c84d62fc915aefeb3 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 3 May 2024 00:41:45 +0200 Subject: [PATCH] feat(aio): switch to llama3-based for LLM (#2225) Signed-off-by: mudler --- aio/cpu/text-to-text.yaml | 2 +- aio/gpu-8g/text-to-text.yaml | 2 +- aio/intel/text-to-text.yaml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/aio/cpu/text-to-text.yaml b/aio/cpu/text-to-text.yaml index f2f6aeb4..902b9683 100644 --- a/aio/cpu/text-to-text.yaml +++ b/aio/cpu/text-to-text.yaml @@ -1,7 +1,7 @@ name: gpt-4 mmap: true parameters: - model: huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q2_K.gguf + model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf template: chat_message: | diff --git a/aio/gpu-8g/text-to-text.yaml b/aio/gpu-8g/text-to-text.yaml index dc620a13..902b9683 100644 --- a/aio/gpu-8g/text-to-text.yaml +++ b/aio/gpu-8g/text-to-text.yaml @@ -1,7 +1,7 @@ name: gpt-4 mmap: true parameters: - model: huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q6_K.gguf + model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf template: chat_message: | diff --git a/aio/intel/text-to-text.yaml b/aio/intel/text-to-text.yaml index bd6b87ba..bc11d4d7 100644 --- a/aio/intel/text-to-text.yaml +++ b/aio/intel/text-to-text.yaml @@ -2,7 +2,7 @@ name: gpt-4 mmap: false f16: false parameters: - model: huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q6_K.gguf + model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf template: chat_message: |