winglian's picture
upload model w 800 steps of pretraining on cosmopedia
7908efb verified
{
"_name_or_path": "winglian/mistral-denseformer-7b",
"architectures": [
"MistralDenseFormerForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "winglian/mistral-denseformer-7b--configuration_mistral.MistralDenseFormerConfig",
"AutoModelForCausalLM": "winglian/mistral-denseformer-7b--modeling_mistral.MistralDenseFormerForCausalLM"
},
"bos_token_id": 1,
"dilation": 4,
"dwa_period": 5,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral_denseformer",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0.dev0",
"use_cache": false,
"vocab_size": 32000
}