初始化项目，由ModelHub XC社区提供模型

Model: jinymusim/gpt-czech-poet
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+license: cc-by-sa-4.0
+language:
+- cs
+pipeline_tag: text-generation
+widget:
+- text: '# ABBA # 1900'
+  example_title: ABBA Rhyme Schema
+- text: '# ABAB # 1920'
+  example_title: ABAB Rhyme Schema
+- text: '# AABB # 1900'
+  example_title: AABB Rhyme Schema
+- text: '# AABCCB # 1880'
+  example_title: AABCCB Rhyme Schema
+base_model:
+- lchaloupsky/czech-gpt2-oscar
+---
+
+### Czech Poetry GPT
+GPT2 finetuned on Czech poetry from github project by  
+Institute of Czech Literature, Czech Academy of Sciences.
+
+https://github.com/versotym/corpusCzechVerse
+
+Done using GPT-Czech-Poet
+
+https://github.com/jinymusim/GPT-Czech-Poet
+
+https://arxiv.org/abs/2407.12790
+
+## Usage
+
+Use as any other GPT2 style model 
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("jinymusim/gpt-czech-poet")
+model = AutoModelForCausalLM.from_pretrained("jinymusim/gpt-czech-poet")
+
+# Input Poet Start
+poet_start = "# AABB # 1900\nD"
+poet_start = poet_start.strip()
+tokenized_poet_start = tokenizer.encode(poet_start, return_tensors='pt')
+
+# generated a continuation to it
+out = model.generate(tokenized_poet_start, 
+                                max_length=256,
+                                do_sample=True,
+                                top_k=50
+                                early_stopping=True,
+                                pad_token_id= tokenizer.pad_token_id,
+                                eos_token_id = tokenizer.eos_token_id)
+
+# Decode Poet
+decoded_cont = tokenizer.decode(out[0], skip_special_tokens=True)
+
+print(decoded_cont)
+```

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "lchaloupsky/czech-gpt2-oscar",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "eos_token_ids": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "output_hidden_states": true,
+  "output_past": true,
+  "pad_token_id": 0,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af7731ab55f5092af02479636efae179f7e2cf5156dc08447ec3eccd4cc1c55
+size 497774248

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55890a5427eedfa0b1b155c2d3a783885e2d146ff492badeb1c5422338117055
+size 497805594

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}