From d2b7c5aeae956abb29b5006dc041e6d08a938454 Mon Sep 17 00:00:00 2001
From: Kai Wu <kaiwu@meta.com>
Date: Mon, 18 Nov 2024 18:55:23 -0800
Subject: [PATCH] add quantized model ollama support (#471)

# What does this PR do?
add more quantized model support for ollama.


- [ ] Addresses issue (#issue)


## Test Plan
Tested with ollama docker that run llama3.2 3b 4bit model.
```
root@docker-desktop:/# ollama ps
NAME           ID              SIZE      PROCESSOR    UNTIL
llama3.2:3b    a80c4f17acd5    3.5 GB    100% CPU     3 minutes from now
```
## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
---
 .../remote/inference/ollama/ollama.py         | 20 +++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/llama_stack/providers/remote/inference/ollama/ollama.py b/llama_stack/providers/remote/inference/ollama/ollama.py
index 27bf0088e..70a091b77 100644
--- a/llama_stack/providers/remote/inference/ollama/ollama.py
+++ b/llama_stack/providers/remote/inference/ollama/ollama.py
@@ -44,10 +44,18 @@ model_aliases = [
         "llama3.1:8b-instruct-fp16",
         CoreModelId.llama3_1_8b_instruct.value,
     ),
+    build_model_alias(
+        "llama3.1:8b",
+        CoreModelId.llama3_1_8b_instruct.value,
+    ),
     build_model_alias(
         "llama3.1:70b-instruct-fp16",
         CoreModelId.llama3_1_70b_instruct.value,
     ),
+    build_model_alias(
+        "llama3.1:70b",
+        CoreModelId.llama3_1_70b_instruct.value,
+    ),
     build_model_alias(
         "llama3.2:1b-instruct-fp16",
         CoreModelId.llama3_2_1b_instruct.value,
@@ -56,6 +64,14 @@ model_aliases = [
         "llama3.2:3b-instruct-fp16",
         CoreModelId.llama3_2_3b_instruct.value,
     ),
+    build_model_alias(
+        "llama3.2:1b",
+        CoreModelId.llama3_2_1b_instruct.value,
+    ),
+    build_model_alias(
+        "llama3.2:3b",
+        CoreModelId.llama3_2_3b_instruct.value,
+    ),
     build_model_alias(
         "llama-guard3:8b",
         CoreModelId.llama_guard_3_8b.value,
@@ -68,6 +84,10 @@ model_aliases = [
         "x/llama3.2-vision:11b-instruct-fp16",
         CoreModelId.llama3_2_11b_vision_instruct.value,
     ),
+    build_model_alias(
+        "llama3.2-vision",
+        CoreModelId.llama3_2_11b_vision_instruct.value,
+    ),
 ]