TheBloke's picture
Update HF model after merging LoRA from chtan/gpt4-alpaca-lora_mlp-65b with Llama 65B
6b69e61
raw
history blame
594 Bytes
{
"_name_or_path": "/workspace/models/huggyllama_llama-65b",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 22016,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.1",
"use_cache": true,
"vocab_size": 32000
}