From e2b319db929ce247aedd92717c61f0bf3348d099 Mon Sep 17 00:00:00 2001 From: Javier Martinez Date: Mon, 29 Jul 2024 17:14:46 +0200 Subject: [PATCH] feat: change ollama default model to llama3.1 --- fern/docs/pages/installation/installation.mdx | 4 ++-- fern/docs/pages/installation/troubleshooting.mdx | 2 +- settings-docker.yaml | 2 +- settings-ollama-pg.yaml | 2 +- settings-ollama.yaml | 2 +- settings.yaml | 2 +- 6 files changed, 7 insertions(+), 7 deletions(-) diff --git a/fern/docs/pages/installation/installation.mdx b/fern/docs/pages/installation/installation.mdx index c3d232a..b5a8e5c 100644 --- a/fern/docs/pages/installation/installation.mdx +++ b/fern/docs/pages/installation/installation.mdx @@ -135,14 +135,14 @@ Now, start Ollama service (it will start a local inference server, serving both ollama serve ``` -Install the models to be used, the default settings-ollama.yaml is configured to user mistral 7b LLM (~4GB) and nomic-embed-text Embeddings (~275MB) +Install the models to be used, the default settings-ollama.yaml is configured to user llama3.1 8b LLM (~4GB) and nomic-embed-text Embeddings (~275MB) By default, PGPT will automatically pull models as needed. This behavior can be changed by modifying the `ollama.autopull_models` property. In any case, if you want to manually pull models, run the following commands: ```bash -ollama pull mistral +ollama pull llama3.1 ollama pull nomic-embed-text ``` diff --git a/fern/docs/pages/installation/troubleshooting.mdx b/fern/docs/pages/installation/troubleshooting.mdx index 586f002..50d87de 100644 --- a/fern/docs/pages/installation/troubleshooting.mdx +++ b/fern/docs/pages/installation/troubleshooting.mdx @@ -24,7 +24,7 @@ PrivateGPT uses the `AutoTokenizer` library to tokenize input text accurately. I In your `settings.yaml` file, specify the model you want to use: ```yaml llm: - tokenizer: mistralai/Mistral-7B-Instruct-v0.2 + tokenizer: meta-llama/Meta-Llama-3.1-8B-Instruct ``` 2. **Set Access Token for Gated Models:** If you are using a gated model, ensure the `access_token` is set as mentioned in the previous section. diff --git a/settings-docker.yaml b/settings-docker.yaml index d8037fa..c68da41 100644 --- a/settings-docker.yaml +++ b/settings-docker.yaml @@ -20,7 +20,7 @@ sagemaker: embedding_endpoint_name: ${PGPT_SAGEMAKER_EMBEDDING_ENDPOINT_NAME:} ollama: - llm_model: ${PGPT_OLLAMA_LLM_MODEL:mistral} + llm_model: ${PGPT_OLLAMA_LLM_MODEL:llama3.1} embedding_model: ${PGPT_OLLAMA_EMBEDDING_MODEL:nomic-embed-text} api_base: ${PGPT_OLLAMA_API_BASE:http://ollama:11434} embedding_api_base: ${PGPT_OLLAMA_EMBEDDING_API_BASE:http://ollama:11434} diff --git a/settings-ollama-pg.yaml b/settings-ollama-pg.yaml index b979824..e2104f1 100644 --- a/settings-ollama-pg.yaml +++ b/settings-ollama-pg.yaml @@ -14,7 +14,7 @@ embedding: embed_dim: 768 ollama: - llm_model: mistral + llm_model: llama3.1 embedding_model: nomic-embed-text api_base: http://localhost:11434 diff --git a/settings-ollama.yaml b/settings-ollama.yaml index 13663dc..87d98a6 100644 --- a/settings-ollama.yaml +++ b/settings-ollama.yaml @@ -11,7 +11,7 @@ embedding: mode: ollama ollama: - llm_model: mistral + llm_model: llama3.1 embedding_model: nomic-embed-text api_base: http://localhost:11434 embedding_api_base: http://localhost:11434 # change if your embedding model runs on another ollama diff --git a/settings.yaml b/settings.yaml index cd977a0..935defc 100644 --- a/settings.yaml +++ b/settings.yaml @@ -111,7 +111,7 @@ openai: embedding_api_key: ${OPENAI_API_KEY:} ollama: - llm_model: llama2 + llm_model: llama3.1 embedding_model: nomic-embed-text api_base: http://localhost:11434 embedding_api_base: http://localhost:11434 # change if your embedding model runs on another ollama