islamrokon
commited on
Commit
•
96c71d5
1
Parent(s):
6681f1e
Upload 4 files
Browse files- config.json +2 -7
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
config.json
CHANGED
@@ -1,14 +1,10 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "EleutherAI/pythia-410m",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 0,
|
8 |
-
"classifier_dropout": 0.1,
|
9 |
"eos_token_id": 0,
|
10 |
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout": 0.0,
|
12 |
"hidden_size": 1024,
|
13 |
"initializer_range": 0.02,
|
14 |
"intermediate_size": 4096,
|
@@ -17,12 +13,11 @@
|
|
17 |
"model_type": "gpt_neox",
|
18 |
"num_attention_heads": 16,
|
19 |
"num_hidden_layers": 24,
|
20 |
-
"rope_scaling": null,
|
21 |
"rotary_emb_base": 10000,
|
22 |
"rotary_pct": 0.25,
|
23 |
"tie_word_embeddings": false,
|
24 |
-
"torch_dtype": "
|
25 |
-
"transformers_version": "4.
|
26 |
"use_cache": true,
|
27 |
"use_parallel_residual": true,
|
28 |
"vocab_size": 50304
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"GPTNeoXForCausalLM"
|
4 |
],
|
|
|
5 |
"bos_token_id": 0,
|
|
|
6 |
"eos_token_id": 0,
|
7 |
"hidden_act": "gelu",
|
|
|
8 |
"hidden_size": 1024,
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 4096,
|
|
|
13 |
"model_type": "gpt_neox",
|
14 |
"num_attention_heads": 16,
|
15 |
"num_hidden_layers": 24,
|
|
|
16 |
"rotary_emb_base": 10000,
|
17 |
"rotary_pct": 0.25,
|
18 |
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float16",
|
20 |
+
"transformers_version": "4.24.0",
|
21 |
"use_cache": true,
|
22 |
"use_parallel_residual": true,
|
23 |
"vocab_size": 50304
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"name_or_path": "EleutherAI/gpt-neox-20b",
|
6 |
+
"special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|