llama2-70b-oasst-pre10 / config.json
andreaskoepf's picture
Upload LlamaForCausalLM
b501f58
{
"_name_or_path": "/pure-mlo-scratch/akoepf/checkpoints/llama2-70b-oasst-pre10-hf/",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 32005,
"eos_token_id": 32006,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 2048,
"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": "4.31.0",
"use_cache": true,
"vocab_size": 32007
}