mistral-3b-experiment / config.json
bn22's picture
Add files using upload-large-folder tool
d1c1192 verified
{
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": null,
"hidden_act": "silu",
"hidden_size": 3200,
"initializer_range": 0.02,
"intermediate_size": 8640,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"num_key_value_heads": 32,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 32000
}