Upload 5 files
Browse files- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer_config.json +8 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": 0.1,
|
9 |
+
"dropout": 0.0,
|
10 |
+
"end_token_id": 2,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout": 0.0,
|
14 |
+
"hidden_size": 2048,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 8192,
|
17 |
+
"layer_norm_eps": 1e-05,
|
18 |
+
"max_position_embeddings": 2048,
|
19 |
+
"model_type": "gpt_neox",
|
20 |
+
"n_embd": 2048,
|
21 |
+
"num_attention_heads": 16,
|
22 |
+
"num_hidden_layers": 24,
|
23 |
+
"pad_token_id": 2,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rotary_emb_base": 10000,
|
26 |
+
"rotary_pct": 0.5,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float16",
|
29 |
+
"transformers_version": "4.31.0.dev0",
|
30 |
+
"use_cache": true,
|
31 |
+
"use_parallel_residual": true,
|
32 |
+
"vocab_size": 30008
|
33 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9088c5ddae5f83d110858f9a9001829627e50e7952236ce736aa321575f0874b
|
3 |
+
size 2540195647
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<|sep|>",
|
5 |
+
"<|acc|>",
|
6 |
+
"<|tel|>",
|
7 |
+
"<|rrn|>"
|
8 |
+
],
|
9 |
+
"eos_token": "<|endoftext|>",
|
10 |
+
"pad_token": "<|endoftext|>"
|
11 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"fast_tokenizer": true,
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "<|endoftext|>",
|
7 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
8 |
+
}
|