upload model weights
Browse files- models/gpt2/config.json +31 -0
- models/gpt2/generation_config.json +6 -0
- models/gpt2/merges.txt +0 -0
- models/gpt2/pytorch_model.bin +3 -0
- models/gpt2/tokenizer.json +0 -0
- models/gpt2/tokenizer_config.json +1 -0
- models/gpt2/vocab.json +0 -0
models/gpt2/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_ctx": 1024,
|
14 |
+
"n_embd": 768,
|
15 |
+
"n_head": 12,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"resid_pdrop": 0.1,
|
19 |
+
"summary_activation": null,
|
20 |
+
"summary_first_dropout": 0.1,
|
21 |
+
"summary_proj_to_labels": true,
|
22 |
+
"summary_type": "cls_index",
|
23 |
+
"summary_use_proj": true,
|
24 |
+
"task_specific_params": {
|
25 |
+
"text-generation": {
|
26 |
+
"do_sample": true,
|
27 |
+
"max_length": 50
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"vocab_size": 50257
|
31 |
+
}
|
models/gpt2/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 50256,
|
3 |
+
"eos_token_id": 50256,
|
4 |
+
"transformers_version": "4.26.0.dev0",
|
5 |
+
"_from_model_config": true
|
6 |
+
}
|
models/gpt2/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/gpt2/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c5d3f4b8b76583b422fcb9189ad6c89d5d97a094541ce8932dce3ecabde1421
|
3 |
+
size 548118077
|
models/gpt2/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/gpt2/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model_max_length": 1024}
|
models/gpt2/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|