Upload 7 files

CITATION.bib

@@ -0,0 +1,29 @@
+@misc{Yannic_2022,
+	title = {GPT-4chan},
+	url = {https://gpt-4chan.com/},
+	author = {Yannic, Kilcher},
+	year = 2022
+}
+
+@article{papasavva2020raiders,
+	title = {Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect Board},
+	author = {Antonis Papasavva, Savvas Zannettou, Emiliano De Cristofaro, Gianluca Stringhini, Jeremy Blackburn},
+	journal = {14th International AAAI Conference On Web And Social Media (ICWSM), 2020},
+	year = 2020
+}
+
+@misc{mesh-transformer-jax,
+	author = {Wang, Ben},
+	title = {{Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX}},
+	howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
+	year = 2021,
+	month = May
+}
+
+@misc{gpt-j,
+	author = {Wang, Ben and Komatsuzaki, Aran},
+	title = {{GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model}},
+	howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
+	year = 2021,
+	month = May
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "rotary_dim": 64,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.10.0.dev0",
+  "tokenizer_class": "GPT2Tokenizer",
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "temperature": 1.0,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "use_cache": true,
+  "vocab_size": 50400
+}

gpt4chan_model_meta.xml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<metadata>
+  <identifier>gpt4chan_model</identifier>
+  <collection>datasets_unsorted</collection>
+  <licenseurl>https://www.apache.org/licenses/LICENSE-2.0</licenseurl>
+  <scanner>Internet Archive Python library 3.0.1</scanner>
+  <mediatype>data</mediatype>
+  <uploader>valentino.giudice96@gmail.com</uploader>
+  <title> GPT-4chan Model</title>
+  <publicdate>2022-06-07 01:56:14</publicdate>
+  <addeddate>2022-06-07 01:56:14</addeddate>
+  <curation>[curator]validator@archive.org[/curator][date]20220607020703[/date][comment]checked for malware[/comment]</curation>
+  <creator> Yannic Kilcher</creator>
+  <description>&lt;div&gt;&lt;div&gt;GPT-4chan is a language model fine-tuned from &lt;a href="https://huggingface.co/EleutherAI/gpt-j-6B" rel="nofollow"&gt;GPT-J 6B&lt;/a&gt; on 3.5 years worth of data from 4chan's politically incorrect (/pol/) board, as included in the dataset &lt;span style="border-style:solid;border-color:rgb(229,231,235);"&gt;&lt;a href="https://zenodo.org/record/3606810" rel="nofollow"&gt;Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect Board&lt;/a&gt;&lt;/span&gt;.&lt;/div&gt;&lt;/div&gt;</description>
+  <publisher> Yannic Kilcher</publisher>
+  <language>English</language>
+  <collection>datasets</collection>
+</metadata>

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "gpt-j-6B", "from_slow": true, "tokenizer_class": "GPT2Tokenizer"}