tinydiffusiongemmamoe4m / diffusion_gemma_config_dump.json
shibatch's picture
Upload folder using huggingface_hub
d657346 verified
Raw
History Blame Contribute Delete
3.45 kB
{
"transformers_version": "5.14.1",
"architectures": [
"DiffusionGemmaForBlockDiffusion"
],
"output_hidden_states": false,
"return_dict": true,
"dtype": "float32",
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"text_config": {
"architectures": null,
"output_hidden_states": false,
"return_dict": true,
"dtype": "float32",
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"vocab_size": 1003,
"hidden_size": 128,
"intermediate_size": 384,
"num_hidden_layers": 8,
"num_attention_heads": 4,
"num_key_value_heads": 1,
"head_dim": 32,
"hidden_activation": "gelu_pytorch_tanh",
"max_position_embeddings": 1024,
"initializer_range": 0.02,
"rms_norm_eps": 1e-06,
"pad_token_id": 1000,
"eos_token_id": 1001,
"bos_token_id": 1000,
"tie_word_embeddings": true,
"rope_parameters": {
"full_attention": {
"partial_rotary_factor": 0.25,
"rope_theta": 1000000.0,
"rope_type": "proportional"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"attention_bias": false,
"attention_dropout": 0.0,
"sliding_window": 64,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention"
],
"use_bidirectional_attention": "vision",
"num_global_key_value_heads": 1,
"global_head_dim": 32,
"num_experts": 4,
"top_k_experts": 2,
"moe_intermediate_size": 192,
"_name_or_path": "",
"model_type": "diffusion_gemma_text",
"output_attentions": false
},
"vision_config": {
"architectures": null,
"output_hidden_states": false,
"return_dict": true,
"dtype": "float32",
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"hidden_size": 32,
"intermediate_size": 64,
"num_hidden_layers": 1,
"num_attention_heads": 4,
"num_key_value_heads": 4,
"head_dim": 8,
"hidden_activation": "gelu_pytorch_tanh",
"rms_norm_eps": 1e-06,
"max_position_embeddings": 256,
"attention_bias": false,
"attention_dropout": 0.0,
"rope_parameters": {
"rope_theta": 100.0,
"rope_type": "default"
},
"pooling_kernel_size": 1,
"patch_size": 16,
"position_embedding_size": 64,
"use_clipped_linears": false,
"standardize": false,
"initializer_range": 0.02,
"_name_or_path": "",
"model_type": "gemma4_vision",
"output_attentions": false
},
"boi_token_id": 255999,
"eoi_token_id": 258882,
"image_token_id": 258880,
"initializer_range": 0.02,
"tie_word_embeddings": true,
"canvas_length": 8,
"_name_or_path": "/home/codex/tinyModels/runs/diffusion_gemma_100p_scratch_full220k/checkpoints/full-0080000/hf",
"model_type": "diffusion_gemma",
"output_attentions": false
}