RLM_hingu / task.json
rudrashah's picture
Upload folder using huggingface_hub
9c461fe verified
raw
history blame
3.31 kB
{
"module": "keras_hub.src.models.gemma3.gemma3_causal_lm",
"class_name": "Gemma3CausalLM",
"config": {
"backbone": {
"module": "keras_hub.src.models.gemma3.gemma3_backbone",
"class_name": "Gemma3Backbone",
"config": {
"name": "gemma3_backbone",
"trainable": true,
"vocabulary_size": 262144,
"image_size": null,
"num_layers": 26,
"num_query_heads": 4,
"num_key_value_heads": 1,
"hidden_dim": 1152,
"intermediate_dim": 6912,
"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": null,
"final_logit_soft_cap": null,
"use_sliding_window_attention": true,
"sliding_window_size": 512,
"local_rope_scaling_factor": 1.0,
"global_rope_scaling_factor": 1.0,
"vision_encoder": null,
"layer_norm_epsilon": 1e-06,
"dropout": 0
},
"registered_name": "keras_hub>Gemma3Backbone"
},
"preprocessor": {
"module": "keras_hub.src.models.gemma3.gemma3_causal_lm_preprocessor",
"class_name": "Gemma3CausalLMPreprocessor",
"config": {
"name": "gemma3_causal_lm_preprocessor",
"trainable": true,
"dtype": {
"module": "keras",
"class_name": "DTypePolicy",
"config": {
"name": "float32"
},
"registered_name": null
},
"tokenizer": {
"module": "keras_hub.src.models.gemma3.gemma3_tokenizer",
"class_name": "Gemma3Tokenizer",
"config": {
"name": "gemma3_tokenizer",
"trainable": true,
"dtype": {
"module": "keras",
"class_name": "DTypePolicy",
"config": {
"name": "int32"
},
"registered_name": null
},
"config_file": "tokenizer.json",
"proto": null,
"sequence_length": null,
"add_bos": false,
"add_eos": false
},
"registered_name": "keras_hub>Gemma3Tokenizer"
},
"config_file": "preprocessor.json",
"sequence_length": 256,
"add_start_token": true,
"add_end_token": true,
"num_vision_tokens_per_image": 0,
"max_images_per_prompt": 0
},
"registered_name": "keras_hub>Gemma3CausalLMPreprocessor"
},
"name": "gemma3_causal_lm"
},
"registered_name": "keras_hub>Gemma3CausalLM"
}