miqu-1-103b / config.json
wolfram's picture
6acef145a4270e8b871f7fb14f660eea6fd2eedc6c63eeda7a1ab7c6814c20fa
1761483 verified
raw
history blame
659 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 32768,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 120,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 32000
}