Instructions to use NotoriousH2/gemma-3-1b-it-Math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NotoriousH2/gemma-3-1b-it-Math with Transformers:

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

pipe = pipeline("text-generation", model="NotoriousH2/gemma-3-1b-it-Math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NotoriousH2/gemma-3-1b-it-Math")
model = AutoModelForCausalLM.from_pretrained("NotoriousH2/gemma-3-1b-it-Math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NotoriousH2/gemma-3-1b-it-Math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NotoriousH2/gemma-3-1b-it-Math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NotoriousH2/gemma-3-1b-it-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NotoriousH2/gemma-3-1b-it-Math

SGLang

How to use NotoriousH2/gemma-3-1b-it-Math 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 "NotoriousH2/gemma-3-1b-it-Math" \
    --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": "NotoriousH2/gemma-3-1b-it-Math",
		"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 "NotoriousH2/gemma-3-1b-it-Math" \
        --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": "NotoriousH2/gemma-3-1b-it-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NotoriousH2/gemma-3-1b-it-Math with Docker Model Runner:
```
docker model run hf.co/NotoriousH2/gemma-3-1b-it-Math
```

NotoriousH2 commited on Feb 26

Commit

db739ad

verified ·

1 Parent(s): 5446cde

Upload Gemma3ForCausalLM

Browse files

Files changed (3) hide show

config.json +3 -6
generation_config.json +2 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -9,10 +9,7 @@
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
   "dtype": "bfloat16",
-  "eos_token_id": [
-    1,
-    106
-  ],
   "final_logit_softcapping": null,
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
@@ -52,7 +49,7 @@
   "num_attention_heads": 4,
   "num_hidden_layers": 26,
   "num_key_value_heads": 1,
-  "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_local_base_freq": 10000,
@@ -62,6 +59,6 @@
   "sliding_window_pattern": 6,
   "transformers_version": "4.57.3",
   "use_bidirectional_attention": false,
-  "use_cache": true,
   "vocab_size": 262144
 }

   "bos_token_id": 2,
   "cache_implementation": "hybrid",
   "dtype": "bfloat16",
+  "eos_token_id": 1,
   "final_logit_softcapping": null,
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
   "num_attention_heads": 4,
   "num_hidden_layers": 26,
   "num_key_value_heads": 1,
+  "pad_token_id": 1,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_local_base_freq": 10000,
   "sliding_window_pattern": 6,
   "transformers_version": "4.57.3",
   "use_bidirectional_attention": false,
+  "use_cache": false,
   "vocab_size": 262144
 }

generation_config.json CHANGED Viewed

@@ -3,10 +3,11 @@
   "cache_implementation": "hybrid",
   "do_sample": true,
   "eos_token_id": [
     1,
     106
   ],
-  "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
   "transformers_version": "4.57.3"

   "cache_implementation": "hybrid",
   "do_sample": true,
   "eos_token_id": [
+    1,
     1,
     106
   ],
+  "pad_token_id": 1,
   "top_k": 64,
   "top_p": 0.95,
   "transformers_version": "4.57.3"

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d4ef8d71c14db7e448a09ebe891cfb6bf32c57a9b44499ae0d1c098e48516b6
 size 1999811208

 version https://git-lfs.github.com/spec/v1
+oid sha256:6fa46f2ee0ff78b3929eb742ecb774db451a64233958dc9205337265625c88aa
 size 1999811208