Upload Gemma3nForConditionalGeneration

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,285 @@
+{
+  "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": 2,
+    "conf_num_hidden_layers": 2,
+    "conf_reduction_factor": 4,
+    "conf_residual_weight": 0.5,
+    "gradient_clipping": 10000000000.0,
+    "hidden_size": 64,
+    "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",
+  "text_config": {
+    "activation_sparsity_pattern": [
+      0.95,
+      0.95,
+      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": 32,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 32,
+    "hidden_size_per_layer_input": 2,
+    "initializer_range": 0.02,
+    "intermediate_size": [
+      64,
+      64,
+      64,
+      64
+    ],
+    "laurel_rank": 8,
+    "layer_types": [
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3n_text",
+    "num_attention_heads": 1,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 1,
+    "num_kv_shared_layers": 2,
+    "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": "4.53.2",
+  "vision_config": {
+    "architecture": "mobilenetv5_300m_enc",
+    "do_pooling": false,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "label_names": [
+      "LABEL_0",
+      "LABEL_1"
+    ],
+    "model_args": {
+      "block_args": [
+        [
+          {
+            "act_layer": null,
+            "block_type": "er",
+            "exp_kernel_size": 3,
+            "exp_ratio": 4.0,
+            "force_in_chs": 0,
+            "noskip": false,
+            "out_chs": 32,
+            "pw_kernel_size": 1,
+            "se_ratio": 0.0,
+            "stride": 2
+          },
+          {
+            "act_layer": null,
+            "block_type": "er",
+            "exp_kernel_size": 3,
+            "exp_ratio": 4.0,
+            "force_in_chs": 0,
+            "noskip": false,
+            "out_chs": 32,
+            "pw_kernel_size": 1,
+            "se_ratio": 0.0,
+            "stride": 1
+          }
+        ],
+        [
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 5,
+            "dw_kernel_size_start": 3,
+            "exp_ratio": 6.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 2
+          },
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 0,
+            "dw_kernel_size_start": 5,
+            "exp_ratio": 4.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 1
+          },
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 0,
+            "dw_kernel_size_start": 3,
+            "exp_ratio": 4.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 1
+          }
+        ],
+        [
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 5,
+            "dw_kernel_size_start": 5,
+            "exp_ratio": 6.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 2
+          },
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 0,
+            "dw_kernel_size_start": 0,
+            "exp_ratio": 1.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 1
+          },
+          {
+            "act_layer": null,
+            "block_type": "mqa",
+            "dw_kernel_size": 3,
+            "key_dim": 64,
+            "kv_stride": 2,
+            "noskip": false,
+            "num_heads": 2,
+            "out_chs": 32,
+            "stride": 1,
+            "value_dim": 64
+          },
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 0,
+            "dw_kernel_size_start": 0,
+            "exp_ratio": 2.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 1
+          }
+        ],
+        [
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 5,
+            "dw_kernel_size_start": 5,
+            "exp_ratio": 6.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 2
+          },
+          {
+            "act_layer": null,
+            "block_type": "mqa",
+            "dw_kernel_size": 3,
+            "key_dim": 64,
+            "kv_stride": 1,
+            "noskip": false,
+            "num_heads": 2,
+            "out_chs": 32,
+            "stride": 1,
+            "value_dim": 64
+          },
+          {
+            "act_layer": null,
+            "block_type": "uir",
+            "dw_kernel_size_end": 0,
+            "dw_kernel_size_mid": 0,
+            "dw_kernel_size_start": 0,
+            "exp_ratio": 2.0,
+            "noskip": false,
+            "out_chs": 32,
+            "se_ratio": 0.0,
+            "stride": 1
+          }
+        ]
+      ]
+    },
+    "model_type": "gemma3n_vision",
+    "num_classes": 2,
+    "rms_norm_eps": 1e-06,
+    "torch_dtype": "bfloat16",
+    "vocab_offset": 262144,
+    "vocab_size": 128
+  },
+  "vision_soft_tokens_per_image": 256
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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": "4.53.2",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07cf4ccabeb400baa5b96ad6df316bb7ff86578f9450bf5b1e2a226e15c448f5
+size 23576116