From bfa74b386ac7b2039f0d0bf4f4e4b8bb506a9b08 Mon Sep 17 00:00:00 2001 From: Kleczyk Date: Thu, 4 Apr 2024 11:56:36 +0200 Subject: [PATCH] spell check and improvement --- .gitignore | 2 +- README.md | 8 ++++---- embedding/README.md | 8 ++++---- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/.gitignore b/.gitignore index 3596eeb..33d1754 100644 --- a/.gitignore +++ b/.gitignore @@ -5,6 +5,6 @@ models/** db/ static/ .idea/ -embeding/models/ + **/__pycache__/ diff --git a/README.md b/README.md index f16ada0..e2483e5 100644 --- a/README.md +++ b/README.md @@ -63,7 +63,7 @@ docker compose --profile prod up ``` -### Dowload embeding and llm(must have for servis llm and embedning-api to work) +### Download embedding and llm(must have for services llm and embedding-api to work) ### Embedding api @@ -75,15 +75,15 @@ What you need: - GPU from nvidia ```sh -cd embeding/models +cd embedding/models git clone git@hf.co:intfloat/e5-large-v2 ``` Check the embeding-api docs here: -More info in [README.md](./embedding/README.md) from embeding_models/ +More info in [README.md](./embedding/README.md) from embedding/ -### Download llm model (must have for servis llm to work !!!) +### Download llm model (must have for service llm to work !!!) Download model (size of file 3.6GB ): diff --git a/embedding/README.md b/embedding/README.md index 37535d4..becbc79 100644 --- a/embedding/README.md +++ b/embedding/README.md @@ -6,17 +6,17 @@ 1. Instal git lfs 2. NVIDIA Docker Toolkit -3. Add shh key to hugingface account +3. Add shh key to huggingface account 4. run this in ChatKNML/ : ```sh -cd embeding_models +cd embedding_models git clone git@hf.co:intfloat/e5-large-v2 ``` ### Aleternativ for 1,2,3 -Copy evry flie form here: +Copy every file form here: #### IMPORTANT @@ -56,6 +56,6 @@ from `docker-compose.yml` remove: ``` -#### MOST IMPORTANT DONT PUSH THIS CHANGE +#### MOST IMPORTANT DON'T PUSH THIS CHANGE #### Rest like in GPU option GLHF