Instructions to use DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning with Transformers:

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

pipe = pipeline("image-text-to-text", model="DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning

SGLang

How to use DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning 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 "DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning" \
    --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": "DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning",
		"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 "DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning" \
        --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": "DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning 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 DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning 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 DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning",
    max_seq_length=2048,
)

Docker Model Runner
How to use DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning with Docker Model Runner:
```
docker model run hf.co/DavidAU/Gemma-3-27b-it-Gemini-Deep-Reasoning
```

DavidAU commited on Feb 21

Commit

32fe9b3

verified ·

1 Parent(s): 44bda55

Update README.md

Browse files

Files changed (1) hide show

README.md +39 -0

README.md CHANGED Viewed

@@ -79,6 +79,45 @@ Even when it is in "instruct" mode; this tuning will help model output quality.
 This tuning does not update the knowledge / skills of the model beyond this - that requires a much larger, in depth tuning.
 ---
 <B>OPTIONAL: System prompts</B>

 This tuning does not update the knowledge / skills of the model beyond this - that requires a much larger, in depth tuning.
+Image processing is intact and fully functional.
+Reasoning affects:
+- Image "intelligence"
+- Output generation
+Model Features:
+- 128k context
+- Temp range .1 to 2.5.
+- Reasoning is temp stable.
+- You can activate using "think deeply: prompt" (not required in most cases)
+- System prompt will affect image, reasoning and output generation.
+- System prompt / template NOT required for reasoning generation in most cases.
+Benchmarks are off the scale.
+Enjoy the freedom!
+---
+SPECIAL THANKS TO:
+- Team "TeichAI" for the excellent dataset.
+- Team "Nightmedia" for the benchmarking and colab'ing.
+- Team "Unsloth" for making the training painless.
+BENCHMARKS:
+```
+arc_challenge,arc_easy,boolq,hellaswag,openbookqa,piqa,   winogrande
+0.590        ,0.742   ,0.883,0.781    ,0.458     ,0.822  ,0.751
+```
+VS (Heretic, uncensored base):
+```
+0.557        ,0.711   ,0.868,0.533    ,0.452     ,0.706  ,0.695
+```
 ---
 <B>OPTIONAL: System prompts</B>