Samarth16k/gemma3-finetuned-hf

This is a `Gemma3` model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends. This model is related to a CausalLM task.

Model config:

• —name: gemma3_backbone
• —trainable: True
• —dtype: {'module': 'keras', 'classname': 'DTypePolicy', 'config': {'name': 'float32'}, 'registeredname': None}
• —vocabulary_size: 262144
• —image_size: 896
• —num_layers: 34
• —num_query_heads: 8
• —num_key_value_heads: 4
• —hidden_dim: 2560
• —intermediate_dim: 10240
• —head_dim: 256
• —query_head_dim_normalize: True
• —use_query_key_norm: True
• —use_post_ffw_norm: True
• —use_post_attention_norm: True
• —attention_logit_soft_cap: None
• —final_logit_soft_cap: None
• —use_sliding_window_attention: True
• —sliding_window_size: 1024
• —local_rope_scaling_factor: 1.0
• —global_rope_scaling_factor: 8.0
• —vision_encoder: {'module': 'kerashub.src.models.gemma3.gemma3visionencoder', 'classname': 'Gemma3VisionEncoder', 'config': {'name': 'gemma3visionencoder', 'trainable': False, 'dtype': {'module': 'keras', 'classname': 'DTypePolicy', 'config': {'name': 'float32'}, 'registeredname': None}, 'numheads': 16, 'hiddendim': 1152, 'numlayers': 27, 'intermediatedim': 4304, 'outputdim': 2560, 'poolsize': 4, 'imagesize': 896, 'patchsize': 14, 'layernormepsilon': 1e-06}, 'registeredname': 'kerashub>Gemma3VisionEncoder'}
• —use_bidirectional_attention: False
• —layer_norm_epsilon: 1e-06
• —dropout: 0
• —is_embedding_model: False
• —pooling_intermediate_dim: None
• —embedding_dim: None

This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.