Swallow-70b-NVE-hf / config.json
okoge's picture
Update config.json
9e955dd verified
{
"_name_or_path": "tokyotech-llm/Swallow-70b-NVE-hf",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 4096,
"max_sequence_length": 4096,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.2",
"use_cache": true,
"vocab_size": 32000
}