pretrained-on-lmsys / config.json
akh99's picture
Training in progress, epoch 0
8cfc458 verified
raw
history blame
1.11 kB
{
"_name_or_path": "google/gemma-2-9b-it",
"architectures": [
"Gemma2ForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": 50.0,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": 1,
"final_logit_softcapping": 30.0,
"head_dim": 256,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 3584,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"initializer_range": 0.02,
"intermediate_size": 14336,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_position_embeddings": 8192,
"model_type": "gemma2",
"num_attention_heads": 16,
"num_hidden_layers": 42,
"num_key_value_heads": 8,
"pad_token_id": 0,
"problem_type": "single_label_classification",
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 4096,
"sliding_window_size": 4096,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.1",
"use_cache": false,
"vocab_size": 256000
}