Qwen-1_8B-Chat-llama / config.json
KnutJaegersberg's picture
Upload 8 files
a84c112 verified
raw
history blame
541 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5504,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0",
"use_cache": true,
"vocab_size": 151936,
"attention_bias": true
}