Commit
•
1925fef
1
Parent(s):
2076a90
Upload 9 files (#1)
Browse files- Upload 9 files (54247f61668a2a47f0091c15f33366c177f81f03)
Co-authored-by: Antik <antikpatel128@users.noreply.huggingface.co>
- trained_gpt2_jokes/5/added_tokens.json +3 -0
- trained_gpt2_jokes/5/config.json +41 -0
- trained_gpt2_jokes/5/generation_config.json +6 -0
- trained_gpt2_jokes/5/merges.txt +0 -0
- trained_gpt2_jokes/5/pytorch_model.bin +3 -0
- trained_gpt2_jokes/5/special_tokens_map.json +6 -0
- trained_gpt2_jokes/5/tf_model.h5 +3 -0
- trained_gpt2_jokes/5/tokenizer_config.json +24 -0
- trained_gpt2_jokes/5/vocab.json +0 -0
trained_gpt2_jokes/5/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50256
|
3 |
+
}
|
trained_gpt2_jokes/5/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./trained_gpt2_jokes/5",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 1024,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"predict_special_tokens": true,
|
22 |
+
"reorder_and_upcast_attn": false,
|
23 |
+
"resid_pdrop": 0.1,
|
24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
25 |
+
"scale_attn_weights": true,
|
26 |
+
"summary_activation": null,
|
27 |
+
"summary_first_dropout": 0.1,
|
28 |
+
"summary_proj_to_labels": true,
|
29 |
+
"summary_type": "cls_index",
|
30 |
+
"summary_use_proj": true,
|
31 |
+
"task_specific_params": {
|
32 |
+
"text-generation": {
|
33 |
+
"do_sample": true,
|
34 |
+
"max_length": 50
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.34.0",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
trained_gpt2_jokes/5/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.34.0"
|
6 |
+
}
|
trained_gpt2_jokes/5/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trained_gpt2_jokes/5/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4463e5da8283d6134256d09475105cfc4da91159dc06d61d4f8b6dae295d3041
|
3 |
+
size 1419387869
|
trained_gpt2_jokes/5/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
trained_gpt2_jokes/5/tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56f1508676ad7aa8944bcb31cdcfbea3f82caeba0149c5681e98b67cb5a8bec1
|
3 |
+
size 1419647984
|
trained_gpt2_jokes/5/tokenizer_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": false
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"additional_special_tokens": [],
|
15 |
+
"bos_token": "<|endoftext|>",
|
16 |
+
"clean_up_tokenization_spaces": true,
|
17 |
+
"eos_token": "<|endoftext|>",
|
18 |
+
"errors": "replace",
|
19 |
+
"model_max_length": 1024,
|
20 |
+
"pad_token": "<|endoftext|>",
|
21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
22 |
+
"tokenizer_file": "/home/rnd/.cache/huggingface/hub/models--gpt2-medium/snapshots/f65d4965d1221eff2bcf34f53a2ba12120e18f24/tokenizer.json",
|
23 |
+
"unk_token": "<|endoftext|>"
|
24 |
+
}
|
trained_gpt2_jokes/5/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|