Instructions to use Sweaterdog/Andy-3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Sweaterdog/Andy-3.5 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Sweaterdog/Andy-3.5:Q4_K_M # Run inference directly in the terminal: llama cli -hf Sweaterdog/Andy-3.5:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Sweaterdog/Andy-3.5:Q4_K_M # Run inference directly in the terminal: llama cli -hf Sweaterdog/Andy-3.5:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Sweaterdog/Andy-3.5:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Sweaterdog/Andy-3.5:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Sweaterdog/Andy-3.5:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sweaterdog/Andy-3.5:Q4_K_M
Use Docker
docker model run hf.co/Sweaterdog/Andy-3.5:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Sweaterdog/Andy-3.5 with Ollama:
ollama run hf.co/Sweaterdog/Andy-3.5:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Sweaterdog/Andy-3.5 with Docker Model Runner:
docker model run hf.co/Sweaterdog/Andy-3.5:Q4_K_M
- Lemonade
How to use Sweaterdog/Andy-3.5 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sweaterdog/Andy-3.5:Q4_K_M
Run and chat with the model
lemonade run user.Andy-3.5-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Create READMENOW.MD
Browse files- small-reasoning/READMENOW.MD +17 -0
small-reasoning/READMENOW.MD
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Thanks for reading!
|
| 2 |
+
|
| 3 |
+
Now, with the reasoning models, currently and for all future reference, you HAVE to make code changes to ensure proper usage of the model, and so the history doesn't get flooded with thoughts.
|
| 4 |
+
|
| 5 |
+
In this folder, there is a file named **"local.js"**, download it.
|
| 6 |
+
|
| 7 |
+
Once local.js is installed, go into your MindCraft folder, src, then models, and there you will see a file named **"local.js"**
|
| 8 |
+
|
| 9 |
+
Once you have located local.js, **Delete that file**, we will be replacing it.
|
| 10 |
+
|
| 11 |
+
Once deleted, find the **local.js** file you downloaded, and put it in the directory where the *original* local.js file was.
|
| 12 |
+
|
| 13 |
+
After this, you are finished, and can now use ollama to create the model, and play.
|
| 14 |
+
|
| 15 |
+
## Changes made with the code
|
| 16 |
+
|
| 17 |
+
The code changes are minimal, it simply deletes all data within the models thoughts, where it is held between \<think> and \</think>
|