Upload 4 files
Browse files- config.json +40 -0
- gptlaika_model_meta.sqlite +0 -0
- gptlaika_model_meta.xml +18 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTJForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.0,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gptj",
|
| 14 |
+
"n_embd": 4096,
|
| 15 |
+
"n_head": 16,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 28,
|
| 18 |
+
"n_positions": 2048,
|
| 19 |
+
"resid_pdrop": 0.0,
|
| 20 |
+
"rotary": true,
|
| 21 |
+
"rotary_dim": 64,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"text-generation": {
|
| 30 |
+
"do_sample": true,
|
| 31 |
+
"max_length": 50,
|
| 32 |
+
"temperature": 1.0
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"tie_word_embeddings": false,
|
| 36 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 37 |
+
"transformers_version": "4.18.0.dev0",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50400
|
| 40 |
+
}
|
gptlaika_model_meta.sqlite
ADDED
|
Binary file (20.5 kB). View file
|
|
|
gptlaika_model_meta.xml
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
| 2 |
+
<metadata>
|
| 3 |
+
<identifier>gpt4chan_model</identifier>
|
| 4 |
+
<collection>datasets_unsorted</collection>
|
| 5 |
+
<licenseurl>https://www.apache.org/licenses/LICENSE-2.0</licenseurl>
|
| 6 |
+
<scanner>Internet Archive Python library 3.0.1</scanner>
|
| 7 |
+
<mediatype>data</mediatype>
|
| 8 |
+
<uploader>valentino.giudice96@gmail.com</uploader>
|
| 9 |
+
<title> GPT-4chan Model</title>
|
| 10 |
+
<publicdate>2022-06-07 01:56:14</publicdate>
|
| 11 |
+
<addeddate>2022-06-07 01:56:14</addeddate>
|
| 12 |
+
<curation>[curator]validator@archive.org[/curator][date]20220607020703[/date][comment]checked for malware[/comment]</curation>
|
| 13 |
+
<creator> Yannic Kilcher</creator>
|
| 14 |
+
<description><div><div>GPT-4chan is a language model fine-tuned from <a href="https://huggingface.co/EleutherAI/gpt-j-6B" rel="nofollow">GPT-J 6B</a> on 3.5 years worth of data from 4chan's politically incorrect (/pol/) board, as included in the dataset <span style="border-style:solid;border-color:rgb(229,231,235);"><a href="https://zenodo.org/record/3606810" rel="nofollow">Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect Board</a></span>.</div></div></description>
|
| 15 |
+
<publisher> Yannic Kilcher</publisher>
|
| 16 |
+
<language>English</language>
|
| 17 |
+
<collection>datasets</collection>
|
| 18 |
+
</metadata>
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc396bb082401c3c10daa1f0174d10782d95218181a8a6994f6112eb09d5a7e2
|
| 3 |
+
size 24207819307
|