26 lines
597 B
JSON
26 lines
597 B
JSON
{
|
|
"_name_or_path": "Xenova/llama2.c-stories42M",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 512,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 1376,
|
|
"max_position_embeddings": 1024,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 8,
|
|
"num_hidden_layers": 8,
|
|
"num_key_value_heads": 8,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "4.33.2",
|
|
"use_cache": true,
|
|
"vocab_size": 32000
|
|
}
|