初始化项目，由ModelHub XC社区提供模型

Model: pranavpsv/gpt2-genre-story-generator
Source: Original Platform

.gitattributes

@@ -0,0 +1,9 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,32 @@
+
+# GPT2 Genre Based Story Generator
+
+## Model description
+
+GPT2 fine-tuned on genre-based story generation.
+
+## Intended uses
+
+Used to generate stories based on user inputted genre and starting prompts.
+
+## How to use
+
+#### Supported Genres
+superhero, action, drama, horror, thriller, sci_fi
+#### Input text format
+\<BOS> \<genre> Some optional text...
+
+**Example**: \<BOS> \<sci_fi> After discovering time travel,
+
+```python
+# Example of usage
+from transformers import pipeline
+
+story_gen = pipeline("text-generation", "pranavpsv/gpt2-genre-story-generator")
+print(story_gen("<BOS> <superhero> Batman"))
+
+```
+
+## Training data
+
+Initialized with pre-trained weights of "gpt2" checkpoint. Fine-tuned the model on stories of various genres.

added_tokens.json

@@ -0,0 +1 @@
+{"<BOS>": 50257, "<EOS>": 50258, "<PAD>": 50259, "<superhero>": 50260, "<action>": 50261, "<drama>": 50262, "<thriller>": 50263, "<horror>": 50264, "<sci_fi>": 50265}

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "vocab_size": 50266
+}

eval_results_lm.txt

@@ -0,0 +1 @@
+perplexity = 8.394471294250971

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698d4b92076187fa1cd6e71023255cca717cd909ed84ad4fa354bb462ebe7e59
+size 497791768

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38eb726c71240ed4e9d01eb63101c31151b9eb9d380f3e4bc3d750e9167f0ebb
+size 510404559

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<BOS>", "eos_token": "<EOS>", "unk_token": "<|endoftext|>", "pad_token": "<PAD>", "additional_special_tokens": ["<superhero>", "<action>", "<drama>", "<thriller>", "<horror>", "<sci_fi>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35f7ab9727b6267ada1382b9940c3a532bc2bd8a47ca5ceb4777a81cc6527fa
+size 1045