File size: 1,322 Bytes
6c4d051 |
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 |
{
"_name_or_path": "team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0",
"architectures": [
"TanukiForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_tanuki.TanukiConfig",
"AutoModelForCausalLM": "modeling_tanuki.TanukiForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 4096,
"model_type": "Tanuki",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_experts_per_topk": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 8,
"output_router_logits": false,
"quantization_config": {
"bits": 8,
"checkpoint_format": "gptq",
"damp_percent": 0.01,
"desc_act": false,
"group_size": 128,
"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": 500000.0,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 65024
}
|