Instructions to use trl-internal-testing/tiny-Gemma2ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Gemma2ForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-Gemma2ForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Gemma2ForCausalLM")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Gemma2ForCausalLM", device_map="auto")
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 Settings

vLLM

How to use trl-internal-testing/tiny-Gemma2ForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Gemma2ForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-Gemma2ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-Gemma2ForCausalLM

SGLang

How to use trl-internal-testing/tiny-Gemma2ForCausalLM 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 "trl-internal-testing/tiny-Gemma2ForCausalLM" \
    --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": "trl-internal-testing/tiny-Gemma2ForCausalLM",
		"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 "trl-internal-testing/tiny-Gemma2ForCausalLM" \
        --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": "trl-internal-testing/tiny-Gemma2ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-Gemma2ForCausalLM with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Gemma2ForCausalLM
```

qgallouedec HF Staff commited on Aug 2, 2025

Commit

4e5a02f

verified ·

1 Parent(s): 7b85283

Upload Gemma2ForCausalLM

Browse files

Files changed (3) hide show

config.json +5 -2
generation_config.json +1 -2
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -6,7 +6,6 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
-  "cache_implementation": "hybrid",
   "eos_token_id": 1,
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
@@ -14,6 +13,10 @@
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
   "max_position_embeddings": 8192,
   "model_type": "gemma2",
   "num_attention_heads": 4,
@@ -25,7 +28,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.0.dev0",
   "use_cache": true,
   "vocab_size": 256249
 }

   "attention_dropout": 0.0,
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "eos_token_id": 1,
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 8192,
   "model_type": "gemma2",
   "num_attention_heads": 4,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "torch_dtype": "float32",
+  "transformers_version": "4.55.0.dev0",
   "use_cache": true,
   "vocab_size": 256249
 }

generation_config.json CHANGED Viewed

@@ -1,8 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 2,
-  "cache_implementation": "hybrid",
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.47.0.dev0"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
+  "transformers_version": "4.55.0.dev0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:491fa58cc62fddb3e3ca26f5e7ef2ae38742432ba95a4fd8c4183276a0bb1fa2
 size 8405552

 version https://git-lfs.github.com/spec/v1
+oid sha256:3c553714d961ce15585363bf35e318a9a32ad55182f2b70a6ddf55cd4866a656
 size 8405552