axolotlLLM / config.json
eugenepentland's picture
Training in progress, step 25
11a9c1b
raw
history blame contribute delete
647 Bytes
{
"_name_or_path": "JackFram/llama-68m",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 2,
"num_key_value_heads": 12,
"pad_token_id": 1,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.34.0.dev0",
"use_cache": false,
"vocab_size": 32000
}