39 lines
1.2 KiB
JSON
39 lines
1.2 KiB
JSON
{
|
|
"_name_or_path": "/pscratch/sd/z/zhihanz/models/mistral_4B_hmp_frommeta55k/model_meta55k_hmp4k",
|
|
"architectures": [
|
|
"MistralForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_mistral.MistralConfig",
|
|
"AutoModel": "modeling_mistral.MistralModel",
|
|
"AutoModelForCausalLM": "modeling_mistral.MistralForCausalLM",
|
|
"AutoModelForMaskedLM": "modeling_mistral.MistralForMaskedLM",
|
|
"AutoModelForSequenceClassification": "modeling_mistral.MistralForSequenceClassification"
|
|
},
|
|
"bos_token_id": 1,
|
|
"classifier_dropout": 0.1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 3072,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 16384,
|
|
"is_causal": true,
|
|
"max_position_embeddings": 32768,
|
|
"model_type": "mistral",
|
|
"num_attention_heads": 12,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 4,
|
|
"output_router_logits": false,
|
|
"pad_token_id": 3,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 1000000.0,
|
|
"router_aux_loss_coef": 0.02,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.38.2",
|
|
"use_cache": true,
|
|
"vocab_size": 4096
|
|
}
|