feat: run ollama & llama3

docs/examples.md

@@ -7,6 +7,8 @@ All examples that can be run:
 | Example | Type | Model Size | Image Size | Command | Device |
 | ------------------------------------------------ | ------------------------ | ---------- | ---------- | -------------------------------------------- | -------- |
 | text-generation-webui | Text (LLM) | 3.9GB | 14.8GB | `reComputer run text-generation-webui` | |
+| llama3 | Text (LLM) | 4.9GB | 10.5GB | `reComputer run llama3` | |
+| [ollama](https://github.com/ollama/ollama) | Inference Server | * | 10.5GB | `reComputer run ollama` | |
 | LLaMA | Text (LLM) | 1.5GB | 10.5GB | `reComputer run Sheared-LLaMA-2.7B-ShareGPT` | |
 | llava-v1.5 | Text + Vision (VLM) | 13GB | 14.4GB | `reComputer run llava-v1.5-7b` | |
 | llava-v1.6 | Text + Vision (VLM) | 13GB | 20.3GB | `reComputer run llava-v1.6-vicuna-7b` | |

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "jetson-examples"
-version = "0.0.5"
+version = "0.0.6"
 authors = [{ name = "luozhixin", email = "[email protected]" }]
 description = "Running Gen AI models and applications on NVIDIA Jetson devices with one-line command"
 readme = "README.md"

reComputer/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.5"
+__version__ = "0.0.6"

reComputer/scripts/llama3/run.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+# try stop old server
+docker rm -f ollama
+# start new server
+./run.sh -d --name ollama $(./autotag ollama)
+# run a client
+./run.sh $(./autotag ollama) /bin/ollama run llama3
+# clean new server
+docker rm -f ollama

reComputer/scripts/ollama/run.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+# try stop old server
+docker rm -f ollama
+# run Front-end
+./run.sh $(./autotag ollama)
+# user only can access with http:https://ip:11434