Reshinth
commited on
Commit
•
8d12871
1
Parent(s):
414e73c
Adding init model
Browse files- config.json +25 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"GPTNeoXForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"classifier_dropout": 0.1,
|
7 |
+
"eos_token_id": 0,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_size": 2560,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 10240,
|
12 |
+
"layer_norm_eps": 1e-05,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "gpt_neox",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"rotary_emb_base": 10000,
|
18 |
+
"rotary_pct": 0.25,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "float16",
|
21 |
+
"transformers_version": "4.30.2",
|
22 |
+
"use_cache": true,
|
23 |
+
"use_parallel_residual": true,
|
24 |
+
"vocab_size": 49152
|
25 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d35a68e0076eb4e1b6d671ba5a329a83384cf97cdd04a269ffd9e9d370a0182
|
3 |
+
size 6075650877
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 1000000000000000019884624838656,
|
4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
+
}
|