Image-Text-to-Text
MLX
English
multilingual
gemma4
gemma
gemma-4
edge
on-device
apple-silicon
quantization
gptq
aqlm
ple
Instructions to use TheStageAI/gemma-4-E2B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TheStageAI/gemma-4-E2B-it with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("TheStageAI/gemma-4-E2B-it") config = load_config("TheStageAI/gemma-4-E2B-it") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload folder using huggingface_hub
Browse files- audio_tower.safetensors +3 -0
- config.json +40 -1
- vision_tower.safetensors +3 -0
audio_tower.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ce35d33d32b1746c18cd9c09ac10e054c28d7ff32f11775c73bd75d1aef9055
|
| 3 |
+
size 173223791
|
config.json
CHANGED
|
@@ -2,7 +2,46 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Gemma4ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"audio_config":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"audio_token_id": 258881,
|
| 7 |
"boa_token_id": 256000,
|
| 8 |
"boi_token_id": 255999,
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Gemma4ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"_name_or_path": "",
|
| 7 |
+
"architectures": null,
|
| 8 |
+
"attention_chunk_size": 12,
|
| 9 |
+
"attention_context_left": 13,
|
| 10 |
+
"attention_context_right": 0,
|
| 11 |
+
"attention_invalid_logits_value": -1000000000.0,
|
| 12 |
+
"attention_logit_cap": 50.0,
|
| 13 |
+
"chunk_size_feed_forward": 0,
|
| 14 |
+
"conv_kernel_size": 5,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"gradient_clipping": 10000000000.0,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 1024,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "LABEL_0",
|
| 21 |
+
"1": "LABEL_1"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"is_encoder_decoder": false,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1
|
| 28 |
+
},
|
| 29 |
+
"model_type": "gemma4_audio",
|
| 30 |
+
"num_attention_heads": 8,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"output_attentions": false,
|
| 33 |
+
"output_hidden_states": false,
|
| 34 |
+
"output_proj_dims": 1536,
|
| 35 |
+
"problem_type": null,
|
| 36 |
+
"residual_weight": 0.5,
|
| 37 |
+
"return_dict": true,
|
| 38 |
+
"rms_norm_eps": 1e-06,
|
| 39 |
+
"subsampling_conv_channels": [
|
| 40 |
+
128,
|
| 41 |
+
32
|
| 42 |
+
],
|
| 43 |
+
"use_clipped_linears": true
|
| 44 |
+
},
|
| 45 |
"audio_token_id": 258881,
|
| 46 |
"boa_token_id": 256000,
|
| 47 |
"boi_token_id": 255999,
|
vision_tower.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b481beb0305cc53e9b8637f743fc8ea5a06be39c8bd5d9ec1fee0906d5c3c89
|
| 3 |
+
size 117601758
|