33 lines
857 B
JSON
33 lines
857 B
JSON
{
|
|
"_name_or_path": "/scratch/leuven/328/vsc32851/transtokenizers/en-nl-mistral/en-nl",
|
|
"additional_special_tokens_ids": [],
|
|
"architectures": [
|
|
"MistralForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 0,
|
|
"cls_token_id": null,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"mask_token_id": null,
|
|
"max_position_embeddings": 32768,
|
|
"model_type": "mistral",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 50256,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 10000.0,
|
|
"sliding_window": 4096,
|
|
"tie_word_embeddings": false,
|
|
"tokenizer_class": "GPT2TokenizerFast",
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.38.1",
|
|
"unk_token_id": 3,
|
|
"use_cache": true,
|
|
"vocab_size": 50257
|
|
}
|