Gerbil-B-3.3m / config.json
crumb's picture
Upload GPTJForCausalLM
1b6bf96
{
"_name_or_path": "model",
"activation_function": "gelu_new",
"architectures": [
"GPTJForCausalLM"
],
"attn_pdrop": 0.0,
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gptj",
"n_embd": 32,
"n_head": 4,
"n_inner": null,
"n_layer": 4,
"n_positions": 2048,
"resid_pdrop": 0.0,
"rotary_dim": 8,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.28.0.dev0",
"use_cache": false,
"vocab_size": 50400
}