Add files using upload-large-folder tool

.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 +1,45 @@
+---
+license: gemma
+library_name: mlx
+pipeline_tag: text-generation
+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
+tags:
+- automatic-speech-recognition
+- automatic-speech-translation
+- audio-text-to-text
+- video-text-to-text
+- mlx
+base_model: google/gemma-3n-E4B
+---
+
+# huseyincavus/gemma-3n-E4B-it-4bit-mlx
+
+This model [huseyincavus/gemma-3n-E4B-it-4bit-mlx](https://huggingface.co/huseyincavus/gemma-3n-E4B-it-4bit-mlx) was
+converted to MLX format from [google/gemma-3n-E4B](https://huggingface.co/google/gemma-3n-E4B)
+using mlx-lm version **0.26.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("huseyincavus/gemma-3n-E4B-it-4bit-mlx")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

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 +1,214 @@
+{
+    "architectures": [
+        "Gemma3nForConditionalGeneration"
+    ],
+    "audio_config": {
+        "conf_attention_chunk_size": 12,
+        "conf_attention_context_left": 13,
+        "conf_attention_context_right": 0,
+        "conf_attention_logit_cap": 50.0,
+        "conf_conv_kernel_size": 5,
+        "conf_num_attention_heads": 8,
+        "conf_num_hidden_layers": 12,
+        "conf_reduction_factor": 4,
+        "conf_residual_weight": 0.5,
+        "gradient_clipping": 10000000000.0,
+        "hidden_size": 1536,
+        "input_feat_size": 128,
+        "model_type": "gemma3n_audio",
+        "rms_norm_eps": 1e-06,
+        "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
+            ]
+        ],
+        "torch_dtype": "bfloat16",
+        "vocab_offset": 262272,
+        "vocab_size": 128
+    },
+    "audio_soft_tokens_per_image": 188,
+    "audio_token_id": 262273,
+    "boa_token_id": 256000,
+    "boi_token_id": 255999,
+    "eoa_token_id": 262272,
+    "eoi_token_id": 262144,
+    "eos_token_id": [
+        1,
+        106
+    ],
+    "image_token_id": 262145,
+    "initializer_range": 0.02,
+    "model_type": "gemma3n",
+    "quantization": {
+        "group_size": 128,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 128,
+        "bits": 4
+    },
+    "text_config": {
+        "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,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0
+        ],
+        "altup_active_idx": 0,
+        "altup_coef_clip": 120.0,
+        "altup_correct_scale": true,
+        "altup_num_inputs": 4,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "final_logit_softcapping": 30.0,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 2048,
+        "hidden_size_per_layer_input": 256,
+        "initializer_range": 0.02,
+        "intermediate_size": [
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384,
+            16384
+        ],
+        "laurel_rank": 64,
+        "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",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention"
+        ],
+        "max_position_embeddings": 32768,
+        "model_type": "gemma3n_text",
+        "num_attention_heads": 8,
+        "num_hidden_layers": 35,
+        "num_key_value_heads": 2,
+        "num_kv_shared_layers": 15,
+        "rms_norm_eps": 1e-06,
+        "rope_local_base_freq": 10000.0,
+        "rope_scaling": null,
+        "rope_theta": 1000000.0,
+        "sliding_window": 512,
+        "torch_dtype": "bfloat16",
+        "use_cache": true,
+        "vocab_size": 262400,
+        "vocab_size_per_layer_input": 262144
+    },
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.53.0.dev0",
+    "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": "4.54.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb2552d677df16d2d61903cf4c9435b8fe224d8eda9a59d67e087a1a94f9ee1
+size 3655761240

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