Sailor2-L-1B-SFT / config.json
dreamerdeo's picture
221012c32482adc89687b654d3d3a178fa4d696ad2609ae8e2f1cc8ac29650b7
5453d36 verified
raw
history blame
660 Bytes
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 48,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}