|
{ |
|
"_name_or_path": "./models/models--team-hatakeyama-phase2--Tanuki-8x8B-dpo-v1.0/snapshots/c507d37c68bfc4c6c6e59d0e3046a4fcfa321faa", |
|
"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": 4, |
|
"group_size": 128, |
|
"modules_to_not_convert": [ |
|
"gate" |
|
], |
|
"quant_method": "awq", |
|
"version": "gemm", |
|
"zero_point": 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": false, |
|
"vocab_size": 65024 |
|
} |
|
|