theblackcat102's picture
upload models at 2500 iterations
04aabb3
raw
history blame contribute delete
794 Bytes
{
"_name_or_path": "facebook/galactica-1.3b",
"_remove_final_layer_norm": false,
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"OPTForCausalLM"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"do_layer_norm_before": true,
"dropout": 0.1,
"enable_bias": true,
"eos_token_id": 2,
"ffn_dim": 8192,
"hidden_size": 2048,
"init_std": 0.02,
"layer_norm_elementwise_affine": true,
"layerdrop": 0.0,
"learned_embeddings": true,
"max_position_embeddings": 2048,
"model_type": "opt",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"pad_token_id": 1,
"scale_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.25.1",
"use_cache": true,
"vocab_size": 50002,
"word_embed_proj_dim": 2048
}