Tanuki-8x8B-dpo-v1.0 / config.json
kanhatakeyama's picture
Duplicate from team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0
46a4471 verified
raw
history blame contribute delete
No virus
1.05 kB
{
"_name_or_path": "/storage5/someya/outputs/sftlab-experiments/8x8B/someya-sft_021-zero3_multi_node_no_offload",
"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,
"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": "bfloat16",
"transformers_version": "4.44.0",
"use_cache": true,
"vocab_size": 65024
}