Instructions to use Monibee-Fudgekins/gemma-coder-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Monibee-Fudgekins/gemma-coder-dev with Transformers:

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

pipe = pipeline("text-generation", model="Monibee-Fudgekins/gemma-coder-dev")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Monibee-Fudgekins/gemma-coder-dev", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Monibee-Fudgekins/gemma-coder-dev with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Monibee-Fudgekins/gemma-coder-dev"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Monibee-Fudgekins/gemma-coder-dev",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Monibee-Fudgekins/gemma-coder-dev

SGLang

How to use Monibee-Fudgekins/gemma-coder-dev 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 "Monibee-Fudgekins/gemma-coder-dev" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Monibee-Fudgekins/gemma-coder-dev",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Monibee-Fudgekins/gemma-coder-dev" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Monibee-Fudgekins/gemma-coder-dev",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use Monibee-Fudgekins/gemma-coder-dev 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 Monibee-Fudgekins/gemma-coder-dev 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 Monibee-Fudgekins/gemma-coder-dev to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Monibee-Fudgekins/gemma-coder-dev to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Monibee-Fudgekins/gemma-coder-dev",
    max_seq_length=2048,
)

Docker Model Runner
How to use Monibee-Fudgekins/gemma-coder-dev with Docker Model Runner:
```
docker model run hf.co/Monibee-Fudgekins/gemma-coder-dev
```

Monibee-Fudgekins commited on 14 days ago

Commit

bf4ec71

verified ·

1 Parent(s): 1f949a2

Update model card (smoke run, pass@1 0.00%)

Browse files

Files changed (1) hide show

README.md +72 -14

README.md CHANGED Viewed

@@ -1,22 +1,80 @@
 ---
 base_model: unsloth/gemma-2-9b-it-bnb-4bit
 tags:
-- text-generation-inference
-- transformers
-- unsloth
-- gemma2
-- trl
-license: apache-2.0
-language:
-- en
 ---
-# Uploaded  model
-- **Developed by:** Monibee-Fudgekins
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-2-9b-it-bnb-4bit
-This gemma2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 ---
+license: gemma
 base_model: unsloth/gemma-2-9b-it-bnb-4bit
+datasets:
+  - sahil2801/CodeAlpaca-20k
+library_name: transformers
+pipeline_tag: text-generation
 tags:
+  - code
+  - coding-assistant
+  - qlora
+  - unsloth
+model-index:
+  - name: gemma-coder-dev
+    results:
+      - task:
+          type: text-generation
+          name: Code generation
+        dataset:
+          type: code-eval
+          name: remote-agent-dev-platform coding_eval
+        metrics:
+          - type: pass@1
+            value: 0.0000
+            name: pass@1 (Python/JS/React/Go/Java/Swift)
 ---
+# gemma-coder-dev
+Coding-focused fine-tune of [`unsloth/gemma-2-9b-it-bnb-4bit`](https://huggingface.co/unsloth/gemma-2-9b-it-bnb-4bit),
+produced automatically by the weekly retrain pipeline in
+[remote-agent-dev-platform](https://github.com/Monibee-Fudgekins/remote-agent-dev-platform). **Last updated: 2026-06-16 17:36 UTC** · run mode: `smoke` ·
+promoted: **False**.
+## Model description
+QLoRA fine-tune of unsloth/gemma-2-9b-it-bnb-4bit specialized for coding assistance. It is the default
+agent model for the remote-agent-dev-platform (served via vLLM on Modal).
+## Intended uses & limitations
+- **Intended:** code generation and assistance in Python, JavaScript/React, Go, Java,
+  and Swift, inside a sandboxed agent that runs/tests the output.
+- **Not intended:** safety-critical use, or running generated code unreviewed.
+- **Limitations:** a small, free-tier-trained model — it can produce incorrect or
+  insecure code. Always review and test. Quality tracks the training data, which is
+  still being built out.
+## Training data
+- Dataset: [`sahil2801/CodeAlpaca-20k`](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
+## Training procedure
+- Method: QLoRA (Unsloth), 4-bit base, LoRA r=16 / alpha=32, lr 2e-4 (cosine),
+  max steps 10, max seq len 2048, optimizer adamw_8bit.
+- Hardware: Kaggle free GPU (weekly GitHub Actions run).
+## Evaluation
+Sandboxed multi-language **pass@1** harness (`finetune/evaluate.py`): the model
+completes functions that are then compiled/run against unit tests. Languages whose
+toolchain is unavailable are skipped.
+**Overall pass@1: 0.00%** over 3 executed problems
+(0 skipped). Promotion threshold: 46%.
+| language | passed / run | pass@1 |
+|---|---|---|
+| python | 0/3 | 0.00% |
+## How to use
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tok = AutoTokenizer.from_pretrained("Monibee-Fudgekins/gemma-coder-dev")
+model = AutoModelForCausalLM.from_pretrained("Monibee-Fudgekins/gemma-coder-dev", device_map="auto")
+msgs = [{"role": "user", "content": "Write a Python function that reverses a string."}]
+ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
+print(tok.decode(model.generate(ids, max_new_tokens=256)[0]))
+```
+## Provenance
+Generated by `finetune/kaggle/run.py` in [https://github.com/Monibee-Fudgekins/remote-agent-dev-platform](https://github.com/Monibee-Fudgekins/remote-agent-dev-platform); see that repo for
+the full training + eval pipeline.