Hugging Face's logo

Buckets:
Echelon7
/
Reserve1

Files
xet
Echelon7/Reserve1 / config.json
Echelon7's picture
Echelon7
download
raw
4.1 kB
{
"architectures": [
"LagunaForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_laguna.LagunaConfig",
"AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
},
"model_type": "laguna",
"vocab_size": 100352,
"hidden_size": 2048,
"intermediate_size": 8192,
"num_hidden_layers": 40,
"num_attention_heads": 48,
"num_key_value_heads": 8,
"head_dim": 128,
"max_position_embeddings": 262144,
"attention_bias": false,
"attention_dropout": 0.0,
"rms_norm_eps": 1e-06,
"num_experts": 256,
"num_experts_per_tok": 8,
"moe_intermediate_size": 512,
"shared_expert_intermediate_size": 512,
"norm_topk_prob": true,
"router_aux_loss_coef": 0.0,
"decoder_sparse_step": 1,
"mlp_only_layers": [
0
],
"bos_token_id": 2,
"eos_token_id": [
2,
24
],
"pad_token_id": 9,
"tie_word_embeddings": false,
"use_cache": true,
"torch_dtype": "bfloat16",
"gating": "per-head",
"sliding_window": 512,
"rope_parameters": {
"full_attention": {
"rope_theta": 500000.0,
"rope_type": "yarn",
"factor": 32.0,
"original_max_position_embeddings": 8192,
"beta_slow": 1.0,
"beta_fast": 64.0,
"attention_factor": 1.3465735902799727,
"partial_rotary_factor": 0.5
},
"sliding_attention": {
"rope_type": "default",
"rope_theta": 10000.0,
"partial_rotary_factor": 1.0
}
},
"layer_types": [
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
],
"moe_apply_router_weight_on_input": false,
"mlp_layer_types": [
"dense",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse",
"sparse"
],
"gating_types": [
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head",
"per_head"
],
"moe_routed_scaling_factor": 2.5,
"num_attention_heads_per_layer": [
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64,
48,
64,
64,
64
]
}

Xet Storage Details

Size:
4.1 kB
·
Xet hash:
9c97034ac9d67cd1b8de508334378dd4bdf4927a14ca3a697a98b90fdbf9f0b9

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.