Skip to content

Commit dec9f13

Browse files
authored
[ollama] Add better screenshots (#1457)
* [ollama] Add better screenshots * fix imgs
1 parent e776982 commit dec9f13

File tree

1 file changed

+21
-3
lines changed

1 file changed

+21
-3
lines changed

docs/hub/ollama.md

Lines changed: 21 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,16 @@ Ollama is an application based on llama.cpp to interact with LLMs directly throu
66

77
Getting started is as simple as:
88

9+
1. Enable `ollama` under your [Local Apps settings](https://huggingface.co/settings/local-apps).
10+
2. On a model page, choose `ollama` from `Use this model` dropdown. For example: [bartowski/Llama-3.2-1B-Instruct-GGUF](https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF).
11+
12+
<div class="flex justify-center">
13+
<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/ollama-modelpage-light.gif"/>
14+
<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/ollama-modelpage-dark.gif"/>
15+
</div>
16+
17+
The snippet would be in format:
18+
919
```sh
1020
ollama run hf.co/{username}/{repository}
1121
```
@@ -25,14 +35,22 @@ ollama run hf.co/bartowski/Humanish-LLama3-8B-Instruct-GGUF
2535

2636
By default, the `Q4_K_M` quantization scheme is used, when it's present inside the model repo. If not, we default to picking one reasonable quant type present inside the repo.
2737

28-
To select a different scheme, simply add a tag:
38+
To select a different scheme, simply:
39+
40+
1. From `Files and versions` tab on a model page, open GGUF viewer on a particular GGUF file.
41+
2. Choose `ollama` from `Use this model` dropdown.
42+
43+
<div class="flex justify-center">
44+
<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/ollama-modeltree-light.gif"/>
45+
<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/ollama-modeltree-dark.gif"/>
46+
</div>
47+
48+
The snippet would be in format (quantization tag added):
2949

3050
```sh
3151
ollama run hf.co/{username}/{repository}:{quantization}
3252
```
3353

34-
![guide](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/ollama/guide.png)
35-
3654
For example:
3755

3856
```sh

0 commit comments

Comments
 (0)