Update README.md
Browse files
README.md
CHANGED
@@ -1,31 +1,44 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
model_filename: pytorch_model.bin
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
---
|
28 |
|
|
|
|
|
|
|
|
|
29 |
---
|
30 |
## Hyperameters used
|
31 |
|
@@ -56,10 +69,6 @@ Certainly! Here's a consolidated list of hyperparameters for your QNetworkGPT2 R
|
|
56 |
Researchers can use these hyperparameters to configure and train their QNetworkGPT2 RL models effectively for text generation tasks.
|
57 |
---
|
58 |
|
59 |
-
# QNetworkGPT2: Reinventing Text Generation with AI ππ€
|
60 |
-
|
61 |
-
![Text Generation](https://static.vecteezy.com/system/resources/previews/023/477/674/non_2x/ai-generative-blue-red-ink-splash-illustration-free-png.png)
|
62 |
-
|
63 |
## Overview
|
64 |
|
65 |
QNetworkGPT2 is an extraordinary AI model that marries Reinforcement Learning (RL) with the power of the GPT-2 language model to create impressive text generation experiences. π
|
|
|
1 |
---
|
2 |
+
{
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": ["GPT2LMHeadModel"],
|
5 |
+
"model_filename": "pytorch_model.bin",
|
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": 512,
|
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 |
+
"hidden_dim": 2048,
|
32 |
+
"input_dim": 512,
|
33 |
+
"output_dim": 512
|
34 |
+
}
|
35 |
+
|
36 |
---
|
37 |
|
38 |
+
# QNetworkGPT2: Reinventing Text Generation with AI ππ€
|
39 |
+
|
40 |
+
![Text Generation](https://static.vecteezy.com/system/resources/previews/023/477/674/non_2x/ai-generative-blue-red-ink-splash-illustration-free-png.png)
|
41 |
+
|
42 |
---
|
43 |
## Hyperameters used
|
44 |
|
|
|
69 |
Researchers can use these hyperparameters to configure and train their QNetworkGPT2 RL models effectively for text generation tasks.
|
70 |
---
|
71 |
|
|
|
|
|
|
|
|
|
72 |
## Overview
|
73 |
|
74 |
QNetworkGPT2 is an extraordinary AI model that marries Reinforcement Learning (RL) with the power of the GPT-2 language model to create impressive text generation experiences. π
|