DM05 / config.json
Dexmal's picture
Upload checkpoint
4c78b7f verified
Raw
History Blame Contribute Delete
6.79 kB
{
"action_config": {
"architectures": null,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_implementation": "sdpa",
"attn_logit_softcapping": null,
"bos_token_id": 2,
"chunk_size_feed_forward": 0,
"dtype": null,
"eos_token_id": 1,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 131072,
"model_type": "gemma3_text",
"num_attention_heads": 8,
"num_hidden_layers": 34,
"num_key_value_heads": 4,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"problem_type": null,
"query_pre_attn_scalar": 256,
"return_dict": true,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"factor": 8.0,
"rope_theta": 1000000.0,
"rope_type": "linear"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sliding_window": 4096,
"tie_word_embeddings": true,
"use_bidirectional_attention": false,
"use_cache": true,
"vocab_size": 262208
},
"action_dim": 32,
"architectures": [
"DM05ForConditionalGeneration"
],
"bos_token_id": 2,
"chunk_size": 50,
"dtype": "float32",
"eos_token_id": 1,
"model_type": "dm05",
"pad_token_id": 0,
"tie_word_embeddings": true,
"transformers_version": "5.3.0",
"use_cache": false,
"vlm_config": {
"architectures": [
"Gemma3ForConditionalGeneration"
],
"attn_implementation": {
"": "flex_attention",
"text_config": "flex_attention",
"vision_config": "flash_attention_2"
},
"boi_token_index": 255999,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"eoi_token_index": 256000,
"eos_token_id": [
1,
106
],
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_token_index": 262144,
"initializer_range": 0.02,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"mm_tokens_per_image": 256,
"model_type": "gemma3",
"output_attentions": false,
"output_hidden_states": false,
"problem_type": null,
"return_dict": true,
"text_config": {
"architectures": null,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"eos_token_id": 1,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2560,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 10240,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 131072,
"model_type": "gemma3_text",
"num_attention_heads": 8,
"num_hidden_layers": 34,
"num_key_value_heads": 4,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"problem_type": null,
"query_pre_attn_scalar": 256,
"return_dict": true,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"factor": 8.0,
"rope_theta": 1000000.0,
"rope_type": "linear"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sliding_window": 4096,
"tie_word_embeddings": true,
"use_bidirectional_attention": false,
"use_cache": true,
"vocab_size": 262208
},
"tie_word_embeddings": true,
"use_cache": false,
"vision_config": {
"architectures": null,
"attention_dropout": 0.0,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 448,
"intermediate_size": 4304,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 27,
"output_attentions": false,
"output_hidden_states": false,
"patch_size": 14,
"problem_type": null,
"return_dict": true,
"vision_use_head": false
}
}
}