hf-transformers-bot's picture
Update tiny models for Ministral3ForSequenceClassification
6ccbb1a verified
Raw
History Blame Contribute Delete
942 Bytes
{
"architectures": [
"Ministral3ForSequenceClassification"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 16,
"hidden_act": "gelu",
"hidden_size": 32,
"initializer_range": 0.02,
"intermediate_size": 32,
"max_position_embeddings": 512,
"model_type": "ministral3",
"num_attention_heads": 2,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 16.0,
"llama_4_scaling_beta": 0.1,
"max_position_embeddings": 512,
"mscale": 1.0,
"mscale_all_dim": 1.0,
"original_max_position_embeddings": 16384,
"rope_theta": 1000000.0,
"rope_type": "yarn",
"type": "yarn"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.16.0.dev0",
"use_cache": true,
"vocab_size": 99
}