File size: 1,519 Bytes
087a9bf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
{
"_attn_implementation": "sdpa",
"_name_or_path": "/model/GRIN-MoE",
"architectures": [
"GRIN-MoE"
],
"attention_bias": true,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_grinmoe.GRINMoEConfig",
"AutoModelForCausalLM": "modeling_grinmoe.GRINMoEForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_dropout": 0.0,
"hidden_size": 4096,
"initializer_range": 0.02,
"input_jitter_noise": 0.01,
"intermediate_size": 6400,
"lm_head_bias": true,
"max_position_embeddings": 4096,
"model_type": "grinmoe",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 16,
"output_router_logits": false,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"damp_auto_increment": 0.0015,
"damp_percent": 0.0025,
"desc_act": false,
"dynamic": null,
"group_size": 128,
"lm_head": false,
"meta": {
"quantizer": "gptqmodel:1.0.3-dev0"
},
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"router_aux_loss_coef": 0.0,
"router_jitter_noise": 0.01,
"sliding_window": 2047,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32064
}
|