matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 07:46:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update import.md

Browse Source
This commit is contained in:
Jeffrey Morgan
2023-10-19 12:17:36 -04:00
committed by GitHub
parent fe6f3b48f7
commit 6b213216d5
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/import.md
View File

@@ -1,6 +1,6 @@
# Import a model
This guide walks through importing a PyTorch, Safetensors or GGUF model from a HuggingFace repo to Ollama.
This guide walks through importing a PyTorch, Safetensors or GGUF model.
## Supported models
@@ -15,7 +15,9 @@ To view a model's architecture, check the `config.json` file in its HuggingFace
## Importing
### Step 1: Clone the HuggingFace repository
### Step 1: Clone the HuggingFace repository (optional)
If the model is currently hosted in a HuggingFace repository, first clone that repository to download the raw model.
```
git lfs install
@@ -23,9 +25,9 @@ git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
cd Mistral-7B-Instruct-v0.1
```
### Step 2: Convert and quantize (for PyTorch and Safetensors)
### Step 2: Convert and quantize to a `.bin` file (optional, for PyTorch and Safetensors)
A [Docker image](https://hub.docker.com/r/ollama/quantize) with the tooling required to convert and quantize models is available.
If the model is in PyTorch or Safetensors format, a [Docker image](https://hub.docker.com/r/ollama/quantize) with the tooling required to convert and quantize models is available.
First, Install [Docker](https://www.docker.com/get-started/).