Instructions to use VANNVISAL/gemma-3-r with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VANNVISAL/gemma-3-r with Transformers:

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

pipe = pipeline("text-generation", model="VANNVISAL/gemma-3-r")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("VANNVISAL/gemma-3-r", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use VANNVISAL/gemma-3-r with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VANNVISAL/gemma-3-r"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VANNVISAL/gemma-3-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VANNVISAL/gemma-3-r

SGLang

How to use VANNVISAL/gemma-3-r 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 "VANNVISAL/gemma-3-r" \
    --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": "VANNVISAL/gemma-3-r",
		"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 "VANNVISAL/gemma-3-r" \
        --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": "VANNVISAL/gemma-3-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use VANNVISAL/gemma-3-r 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 VANNVISAL/gemma-3-r 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 VANNVISAL/gemma-3-r to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VANNVISAL/gemma-3-r to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="VANNVISAL/gemma-3-r",
    max_seq_length=2048,
)

Docker Model Runner
How to use VANNVISAL/gemma-3-r with Docker Model Runner:
```
docker model run hf.co/VANNVISAL/gemma-3-r
```

VANNVISAL commited on Apr 29, 2025

Commit

772ea49

verified ·

1 Parent(s): ba676bd

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +14 -4
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -1,8 +1,9 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -12,18 +13,27 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
   "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false
 }

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2-7b-bnb-4bit",
   "bias": "none",
+  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63add73bf9b8b00ecd6347b3aba4950ffb249ca42fc3453333bd41360dfb63c0
-size 59675008

 version https://git-lfs.github.com/spec/v1
+oid sha256:19ea8d57e6abd4528cfbb117b5e29b052efe639aa8a6ac3fead6f899f0a220c9
+size 161533192