Looped-qwen-pre2 / config.json
summer
Upload folder using huggingface_hub
45b4092 verified
Raw History Blame Contribute Delete
2.91 kB
{
"architectures": [
"LoopedGDNForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_looped_gdn.LoopedGDNConfig",
"AutoModelForCausalLM": "modeling_looped_gdn.LoopedGDNForCausalLM"
},
"dtype": "bfloat16",
"eos_token_id": 248044,
"gate_init_bias": 4.0,
"halt_threshold": null,
"hidden_size": 2048,
"loops": [
4,
4,
4,
4,
4,
4
],
"loops_per_group": 4,
"lora_rank": 128,
"model_type": "looped_gdn",
"num_groups": 6,
"num_hidden_layers": 24,
"pad_token_id": null,
"qwen_config": {
"_name_or_path": "",
"architectures": null,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 2048,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 6144,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"linear_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 16,
"linear_value_head_dim": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 8,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"partial_rotary_factor": 0.25,
"rope_theta": 10000000,
"rope_type": "default"
},
"tie_word_embeddings": true,
"transformers_version": "5.18.0",
"use_cache": true,
"vocab_size": 248320
},
"tie_word_embeddings": true,
"transformers_version": "5.5.0",
"vocab_size": 248320
}