Instructions to use SAXON-AI/SAXON-RURAL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SAXON-AI/SAXON-RURAL with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SAXON-AI/SAXON-RURAL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SAXON-AI/SAXON-RURAL", dtype="auto")

llama-cpp-python

How to use SAXON-AI/SAXON-RURAL with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SAXON-AI/SAXON-RURAL",
	filename="unsloth.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SAXON-AI/SAXON-RURAL with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SAXON-AI/SAXON-RURAL:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SAXON-AI/SAXON-RURAL:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SAXON-AI/SAXON-RURAL:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SAXON-AI/SAXON-RURAL: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 SAXON-AI/SAXON-RURAL:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SAXON-AI/SAXON-RURAL: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 SAXON-AI/SAXON-RURAL:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SAXON-AI/SAXON-RURAL:Q4_K_M

Use Docker

docker model run hf.co/SAXON-AI/SAXON-RURAL:Q4_K_M

LM Studio
Jan

vLLM

How to use SAXON-AI/SAXON-RURAL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SAXON-AI/SAXON-RURAL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SAXON-AI/SAXON-RURAL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SAXON-AI/SAXON-RURAL:Q4_K_M

SGLang

How to use SAXON-AI/SAXON-RURAL with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SAXON-AI/SAXON-RURAL" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SAXON-AI/SAXON-RURAL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SAXON-AI/SAXON-RURAL" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SAXON-AI/SAXON-RURAL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SAXON-AI/SAXON-RURAL with Ollama:
```
ollama run hf.co/SAXON-AI/SAXON-RURAL:Q4_K_M
```

Unsloth Studio new

How to use SAXON-AI/SAXON-RURAL with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SAXON-AI/SAXON-RURAL to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SAXON-AI/SAXON-RURAL to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SAXON-AI/SAXON-RURAL to start chatting

Docker Model Runner
How to use SAXON-AI/SAXON-RURAL with Docker Model Runner:
```
docker model run hf.co/SAXON-AI/SAXON-RURAL:Q4_K_M
```

Lemonade

How to use SAXON-AI/SAXON-RURAL with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SAXON-AI/SAXON-RURAL:Q4_K_M

Run and chat with the model

lemonade run user.SAXON-RURAL-Q4_K_M

List all available models

lemonade list

charlie commited on Feb 13, 2025

Commit

ccf0066

verified ·

1 Parent(s): 9a3e276

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -1

README.md CHANGED Viewed

@@ -1,7 +1,27 @@
 ---
 base_model:
 - SAXON-AI/SAXON-INCEL
 pipeline_tag: text-generation
 ---
-SAXON-RURAL, a mix of SAXON-INCEL and WURZEL.

 ---
 base_model:
 - SAXON-AI/SAXON-INCEL
+- chaphi/wurzel
+library_name: transformers
+tags:
+- mergekit
+- merge
 pipeline_tag: text-generation
 ---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64de406ce437d02ce69630b5/voK3ki1j_1EGQeYxc1jAa.png)
+# SAXON RURAL
+This is an iteration of the SAXON model series, I am attempting to merge the SAXON INCEL model with WURZEL using [SuperMario Safetensors Merger](https://huggingface.co/spaces/mrcuddle/DARE-MERGE-SAFETENSORS) before merging into SAXON-0-I to create SAXON-0-II.
+## Merge Details
+### Merge Method
+This model was merged using the [DARE TIES](https://huggingface.co/blog/kgourgou/a-first-look-at-automerger-data#:~:text=The%20mergekit%20documentation%20describes%20the,performance%20of%20the%20original%20models.) merge method using [SAXON-INCEL](https://huggingface.co/SAXON-AI/SAXON-INCEL) as a base.
+### Models Merged
+The following model was included in the merge:
+* [Wurzel](https://huggingface.co/chaphi/wurzel)