Instructions to use peft-internal-testing/tiny-random-gemma4-E2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use peft-internal-testing/tiny-random-gemma4-E2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="peft-internal-testing/tiny-random-gemma4-E2B")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("peft-internal-testing/tiny-random-gemma4-E2B")
model = AutoModelForImageTextToText.from_pretrained("peft-internal-testing/tiny-random-gemma4-E2B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use peft-internal-testing/tiny-random-gemma4-E2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "peft-internal-testing/tiny-random-gemma4-E2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "peft-internal-testing/tiny-random-gemma4-E2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/peft-internal-testing/tiny-random-gemma4-E2B

SGLang

How to use peft-internal-testing/tiny-random-gemma4-E2B 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 "peft-internal-testing/tiny-random-gemma4-E2B" \
    --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": "peft-internal-testing/tiny-random-gemma4-E2B",
		"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 "peft-internal-testing/tiny-random-gemma4-E2B" \
        --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": "peft-internal-testing/tiny-random-gemma4-E2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use peft-internal-testing/tiny-random-gemma4-E2B with Docker Model Runner:
```
docker model run hf.co/peft-internal-testing/tiny-random-gemma4-E2B
```

BenjaminB HF Staff commited on 26 days ago

Commit

87719b7

verified ·

1 Parent(s): 42534d7

Upload Gemma4ForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +156 -0
generation_config.json +10 -0
model.safetensors +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,156 @@

+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 64,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 32,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 64,
+    "head_dim": 32,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 8,
+    "hidden_size_per_layer_input": 2,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_types": [
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 4,
+    "num_kv_shared_layers": 2,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 32,
+    "head_dim": 32,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 8,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.7.0.dev0",
+  "use_cache": true
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:032cdee368a3cf233b3ec293cff59bdbcf7d39a836d66b34f44337151da85fe0
+size 9470740