EdgeRock / config.json
rockmatrix-ai's picture
Use BF16 inference and align figures and results with the technical report
799fa1f verified
Raw History Blame Contribute Delete
2.62 kB
{
"architectures": [
"EdgeRockForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 248044,
"fixed_memory_parent": "original_qwen3_5_text",
"fixed_memory_revision": "qwen35-text-original-gdn-swa-independent-gqa-memory-v1",
"fixed_memory_swa_layers": [
3,
7,
11,
15,
19,
23,
27,
31
],
"fixed_memory_swa_window": 1024,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 2560,
"independent_memory": {
"admission_rank": 256,
"capacity": 1024,
"max_commit_chunk": 256,
"writer_intermediate_size": 2560
},
"initializer_range": 0.02,
"intermediate_size": 9216,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "edgerock",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"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": "5.7.0.dev0",
"use_cache": true,
"vocab_size": 248320,
"backend": "torch",
"auto_map": {
"AutoConfig": "configuration_edgerock.EdgeRockConfig",
"AutoModel": "modeling_edgerock.EdgeRockModel",
"AutoModelForCausalLM": "modeling_edgerock.EdgeRockForCausalLM"
}
}