Qwen2-Deita-500m / config.json
KnutJaegersberg's picture
Upload 8 files
bef6240 verified
raw
history blame contribute delete
720 Bytes
{
"_name_or_path": "/run/media/knut/HD2/LLMs2/Qwen2-0.5B/",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151646
}