LexMatcher_13B / config.json
lemonzeng's picture
model
dae955a
raw
history blame
680 Bytes
{
"_name_or_path": "/mnt/nanjing3cephfs/pr-others-prctrans/lemonzeng/search/mGPT/models/llama-2-13b",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 2,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.0",
"use_cache": true,
"vocab_size": 32000
}