Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+license: gemma
+library_name: transformers
+pipeline_tag: image-text-to-text
+extra_gated_heading: Access Gemma on Hugging Face
+extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
+  agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+base_model: google/gemma-3n-E4b-it
+tags:
+- automatic-speech-recognition
+- automatic-speech-translation
+- audio-text-to-text
+- video-text-to-text
+- mlx
+---
+
+# mlx-community/gemma-3n-E2B-it-4bit
+This model was converted to MLX format from [`google/gemma-3n-E2B-it`]() using mlx-vlm version **0.2.0**.
+Refer to the [original model card](https://huggingface.co/google/gemma-3n-E2B-it) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/gemma-3n-E2B-it-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

chat_template.jinja

@@ -0,0 +1,49 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'audio' -%}
+                {{ '<audio_soft_token>' }}
+            {%- elif item['type'] == 'image' -%}
+                {{ '<image_soft_token>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,440 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "Gemma3nForConditionalGeneration"
+    ],
+    "audio_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "conf_positional_bias_size": 256,
+        "model_type": "gemma3n_audio",
+        "sscp_conv_eps": 0.001,
+        "input_feat_size": 128,
+        "hidden_size": 1536,
+        "rms_norm_eps": 1e-06,
+        "vocab_size": 128,
+        "vocab_offset": 262272,
+        "gradient_clipping": 10000000000.0,
+        "conf_attention_chunk_size": 12,
+        "conf_attention_context_left": 13,
+        "conf_attention_context_right": 0,
+        "conf_attention_logit_cap": 50.0,
+        "conf_num_attention_heads": 8,
+        "conf_num_hidden_layers": 12,
+        "conf_conv_kernel_size": 5,
+        "conf_reduction_factor": 4,
+        "conf_residual_weight": 0.5,
+        "sscp_conv_channel_size": [
+            128,
+            32
+        ],
+        "sscp_conv_group_norm_eps": 0.001,
+        "sscp_conv_kernel_size": [
+            [
+                3,
+                3
+            ],
+            [
+                3,
+                3
+            ]
+        ],
+        "sscp_conv_stride_size": [
+            [
+                2,
+                2
+            ],
+            [
+                2,
+                2
+            ]
+        ],
+        "output_attentions": false
+    },
+    "audio_soft_tokens_per_image": 188,
+    "audio_token_id": 262273,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "boa_token_id": 256000,
+    "boi_token_id": 255999,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eoa_token_id": 262272,
+    "eoi_token_id": 262144,
+    "eos_token_id": [
+        1,
+        106
+    ],
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "image_token_id": 262145,
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gemma3n",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "text_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 2,
+        "pad_token_id": 0,
+        "eos_token_id": 1,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "altup_lr_multiplier": 1.0,
+        "model_type": "gemma3n_text",
+        "query_pre_attn_scalar": 256,
+        "vocab_size": 262400,
+        "vocab_size_per_layer_input": 262144,
+        "max_position_embeddings": 32768,
+        "hidden_size": 2048,
+        "intermediate_size": [
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192,
+            8192
+        ],
+        "num_hidden_layers": 30,
+        "num_attention_heads": 8,
+        "head_dim": 256,
+        "num_key_value_heads": 2,
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-06,
+        "use_cache": true,
+        "rope_theta": 1000000.0,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "sliding_window": 512,
+        "final_logit_softcapping": 30.0,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention"
+        ],
+        "rope_local_base_freq": 10000.0,
+        "rope_scaling": null,
+        "hidden_size_per_layer_input": 256,
+        "num_kv_shared_layers": 10,
+        "altup_active_idx": 0,
+        "altup_coef_clip": 120.0,
+        "altup_correct_scale": true,
+        "altup_num_inputs": 4,
+        "laurel_rank": 64,
+        "activation_sparsity_pattern": [
+            0.95,
+            0.95,
+            0.95,
+            0.95,
+            0.95,
+            0.95,
+            0.95,
+            0.95,
+            0.95,
+            0.95,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0
+        ],
+        "output_attentions": false
+    },
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.53.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "label_names": [
+            "LABEL_0",
+            "LABEL_1"
+        ],
+        "model_type": "gemma3n_vision",
+        "num_classes": 2,
+        "initializer_range": 0.02,
+        "do_pooling": true,
+        "model_args": null,
+        "architecture": "mobilenetv5_300m_enc",
+        "hidden_size": 2048,
+        "vocab_size": 128,
+        "vocab_offset": 262144,
+        "rms_norm_eps": 1e-06,
+        "output_attentions": false
+    },
+    "vision_soft_tokens_per_image": 256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.53.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3c01535767de53b8ac68d7ccfd93163c1ca763e92ef2d0948b3f54d1bdee58
+size 3786285472

preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_size": 128,
+  "fft_length": 1024,
+  "fft_overdrive": true,
+  "frame_length": 512,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "input_scale_factor": 1.0,
+  "max_frequency": 7600.0,
+  "mel_floor": 1e-05,
+  "min_frequency": 125.0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "per_bin_mean": null,
+  "per_bin_stddev": null,
+  "preemphasis": 0.97,
+  "preemphasis_htk_flavor": true,
+  "processor_class": "Gemma3nProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": false,
+  "return_tensors": null,
+  "sampling_rate": 16000,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

processor_config.json

@@ -0,0 +1,5 @@
+{
+  "audio_seq_length": 188,
+  "image_seq_length": 256,
+  "processor_class": "Gemma3nProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "audio_token": "<audio_soft_token>",
+  "boa_token": "<start_of_audio>",
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoa_token": "<end_of_audio>",
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
+size 33442553

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5f0cc48abfbfc04d14562270a32e02149a3e7035f368cc5a462786f4a59961
+size 4696020