Lake-1-6B-spe / config.json
BICORP's picture
Upload 4 files
b2654cf verified
raw
history blame contribute delete
765 Bytes
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 1010000,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"vocab_size": 152064,
"dual_chunk_attention_config": {
"chunk_size": 262144,
"local_size": 8192,
"original_max_position_embeddings": 262144
}
}