woshixuhang's picture
Upload iquest checkpoint at global_step_500
091b6e2 verified
{
"architectures": [
"IQuestCoderForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_iquestcoder.IQuestCoderConfig",
"AutoModel": "modeling_iquestcoder.IQuestCoderModel",
"AutoModelForCausalLM": "modeling_iquestcoder.IQuestCoderForCausalLM",
"AutoModelForQuestionAnswering": "modeling_iquestcoder.IQuestCoderForQuestionAnswering",
"AutoModelForSequenceClassification": "modeling_iquestcoder.IQuestCoderForSequenceClassification",
"AutoModelForTokenClassification": "modeling_iquestcoder.IQuestCoderForTokenClassification"
},
"bos_token_id": 1,
"clip_qkv": null,
"dtype": "bfloat16",
"eos_token_id": 75864,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 131072,
"max_window_layers": 0,
"mlp_bias": false,
"model_type": "iquestcoder",
"num_attention_heads": 40,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pad_token_id": 75869,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.6",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 76800
}