Instructions to use TheOneWhoWill/Coding-Monkey-Gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheOneWhoWill/Coding-Monkey-Gemma with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-12B-it")
model = PeftModel.from_pretrained(base_model, "TheOneWhoWill/Coding-Monkey-Gemma")

Transformers

How to use TheOneWhoWill/Coding-Monkey-Gemma with Transformers:

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

pipe = pipeline("text-generation", model="TheOneWhoWill/Coding-Monkey-Gemma")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheOneWhoWill/Coding-Monkey-Gemma", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheOneWhoWill/Coding-Monkey-Gemma with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheOneWhoWill/Coding-Monkey-Gemma

SGLang

How to use TheOneWhoWill/Coding-Monkey-Gemma 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 "TheOneWhoWill/Coding-Monkey-Gemma" \
    --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": "TheOneWhoWill/Coding-Monkey-Gemma",
		"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 "TheOneWhoWill/Coding-Monkey-Gemma" \
        --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": "TheOneWhoWill/Coding-Monkey-Gemma",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use TheOneWhoWill/Coding-Monkey-Gemma with Docker Model Runner:
```
docker model run hf.co/TheOneWhoWill/Coding-Monkey-Gemma
```

TheOneWhoWill commited on 2 days ago

Commit

c05997b

verified ·

1 Parent(s): c1e5a7c

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -16

README.md CHANGED Viewed

@@ -54,7 +54,7 @@ That's \~5,161 actual tool-calling examples (\~99% of the set) trained over 3 ep
 ## Quantization
 This model has fp16, Q8_0, Q6_K, Q5_K_M, and Q4_K_M quantization available in the gguf format. You can find them in this [repository](https://huggingface.co/TheOneWhoWill/Coding-Monkey-Gemma-GGUF)
-## Usage
 ### llama.cpp
 To use this model with llama.cpp you can use the ggufs like so
 ```bash
@@ -74,18 +74,8 @@ then you can run it like so with the Modelfile in the same directory as the gguf
 ollama create coding-monkey -f Modelfile
 ```
----
-## Serving & Deploying Fine-Tuned Adapters?
-Tired of merging LoRA weights, converting formats, and running quantization scripts just to get an OpenAI-compatible endpoint?
-Check out **[Lorivo](https://lorivo.dev/)**, a platform built to deploy and serve fine-tuned LoRA adapters instantly with production vLLM backends and standard OpenAI endpoints:
-- **Zero-Merge Serving:** Mount adapters dynamically on top of open-weight base models (Gemma, Qwen, Llama).
-- **Instant OpenAI Compatibility:** Plug directly into Cursor, Cline, Aider, or your custom agent harnesses.
-- **CLI & Web Control:** Deploy from your terminal via `lorivo deploy` or manage endpoints from the dashboard.
-👉 **[Deploy your fine-tuned adapters on Lorivo →](https://lorivo.dev/)**
----

 ## Quantization
 This model has fp16, Q8_0, Q6_K, Q5_K_M, and Q4_K_M quantization available in the gguf format. You can find them in this [repository](https://huggingface.co/TheOneWhoWill/Coding-Monkey-Gemma-GGUF)
+## Usage & Deployment
 ### llama.cpp
 To use this model with llama.cpp you can use the ggufs like so
 ```bash
 ollama create coding-monkey -f Modelfile
 ```
+### Lorivo
+Deploy this model with [Lorivo](https://lorivo.dev/) for a production-ready, OpenAI-compatible API endpoint. Lorivo supports serving fine-tuned LoRA adapters without requiring you to merge the adapter into the base model or manually manage the serving infrastructure. Note: Lorivo currently supports the LoRA adapter format containing adapter_config.json and the associated .safetensors adapter weights. The merged model or GGUF files are not supported for this deployment method.
+```bash
+lorivo deploy ./Coding-Monkey-Gemma
+```