aakarsh-nair's picture
aakarsh-nair/rerun-09-19-2024-experiment-distill-tree-babylm2024-95-0
b526bed verified
raw
history blame contribute delete
699 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 2048,
"max_position_embeddings": 256,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 10,
"num_key_value_heads": 12,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.45.0.dev0",
"use_cache": true,
"vocab_size": 16000
}