cosmoquester
commited on
Commit
·
ac8b6c6
1
Parent(s):
a0a1153
feat: Add model
Browse files- config.json +25 -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 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 0,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_size": 2048,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 8192,
|
12 |
+
"layer_norm_eps": 1e-05,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "gpt_neox",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"rotary_emb_base": 10000,
|
18 |
+
"rotary_pct": 0.5,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "float16",
|
21 |
+
"transformers_version": "4.25.1",
|
22 |
+
"use_cache": true,
|
23 |
+
"use_parallel_residual": true,
|
24 |
+
"vocab_size": 30080
|
25 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44243825427f6a457102d2d7f98d4bbe4b1005548352ce53c2482d13ad2389bf
|
3 |
+
size 2764349516
|
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 |
+
"eos_token": "<|endoftext|>",
|
3 |
+
"model_max_length": 1000000000000000019884624838656,
|
4 |
+
"name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
5 |
+
"pad_token": "<|endoftext|>",
|
6 |
+
"special_tokens_map_file": "/home/cosmoquester/.cache/huggingface/hub/models--EleutherAI--polyglot-ko-1.3b/snapshots/711da2957fdae31202de86c51edbc0c7f433b9e5/special_tokens_map.json",
|
7 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
8 |
+
}
|