Vikhr-7b-0.1 / config.json
AlexWortega's picture
Correcting from Llama to Mistral (#3)
386d754 verified
{
"_name_or_path": "Vikhrmodels/Vikhr-7b-0.1",
"architectures": [
"MistralForCausalLM"
],
"attention_bias": false,
"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,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 40000
}