1231czx's picture
Upload MistralForCausalLM
ae17480 verified
raw
history blame contribute delete
No virus
762 Bytes
{
"_name_or_path": "/home/wexiong_google_com/wx/sft/RLHF-Reward-Modeling/pair-pm/pm_models/mistral_bz64_5e6_pack4096_1200k/checkpoint-482",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 32768,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.1",
"use_cache": false,
"vocab_size": 32769
}