float32 model

This commit is contained in:
Yannic Kilcher 2022-05-17 16:08:08 +02:00
parent 3ece8d9841
commit f5473a777f
2 changed files with 39 additions and 0 deletions

36
config.json Normal file
View File

@ -0,0 +1,36 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPTJForCausalLM"
],
"attn_pdrop": 0.0,
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gptj",
"n_embd": 4096,
"n_head": 16,
"n_layer": 28,
"n_positions": 2048,
"rotary_dim": 64,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"transformers_version": "4.10.0.dev0",
"tokenizer_class": "GPT2Tokenizer",
"task_specific_params": {
"text-generation": {
"do_sample": true,
"temperature": 1.0,
"max_length": 50
}
},
"torch_dtype": "float32",
"use_cache": true,
"vocab_size": 50400
}

3
pytorch_model.bin Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fc396bb082401c3c10daa1f0174d10782d95218181a8a6994f6112eb09d5a7e2
size 24207819307