LN-Korean-14B-v0.2 / config.json
CjangCjengh's picture
Upload files
d328f40
raw
history blame contribute delete
746 Bytes
{
"_name_or_path": "Sakura-14B-Qwen2beta-Base-v2",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13696,
"max_position_embeddings": 32768,
"max_window_layers": 35,
"model_type": "qwen2",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.2",
"use_cache": false,
"use_flash_attention": true,
"use_sliding_window": false,
"vocab_size": 152064
}