初始化项目，由ModelHub XC社区提供模型

Model: radlab/polish-gpt2-small-v2
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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 +1,61 @@
+---
+license: cc-by-4.0
+datasets:
+- clarin-knext/msmarco-pl
+- clarin-knext/nq-pl
+- clarin-knext/hotpotqa-pl
+- clarin-knext/scidocs-pl
+- clarin-knext/nfcorpus-pl
+- clarin-knext/dbpedia-pl
+- clarin-knext/trec-covid-pl
+- clarin-knext/quora-pl
+- clarin-knext/arguana-pl
+- clarin-knext/fiqa-pl
+- radlab/wikipedia-pl
+- radlab/legal-mc4-pl
+language:
+- pl
+library_name: transformers
+tags:
+- gpt2
+- from-scratch
+- polish-gpt2
+---
+
+## Description
+This is the polish gpt2 model in small architecture. 
+
+This model was released on 30.11.2023 and it is the newest version of `radlab/polish-gpt2-small` (https://huggingface.co/radlab/polish-gpt2-small)
+
+
+## Datasets
+Data which are used to train this model:
+- clarin-knext/msmarco-pl
+- clarin-knext/nq-pl
+- clarin-knext/hotpotqa-pl
+- clarin-knext/scidocs-pl
+- clarin-knext/nfcorpus-pl
+- clarin-knext/dbpedia-pl
+- clarin-knext/trec-covid-pl
+- clarin-knext/quora-pl
+- clarin-knext/arguana-pl
+- clarin-knext/fiqa-pl
+- radlab/wikipedia-pl
+- radlab/legal-mc4-pl
+- own corpora not published yet
+
+It is about 30,5 GB of data which is 3 times more than the prevoius version.
+
+
+## Metrics from W&B
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/BBhEM3RL4rM1rOwTG-1RC.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/Z7BKY2vKPXWkQZEybt2rW.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/upsovWy0lVohPGjR1AGmN.png)
+
+## Changelog
+- _2023.11.30_ - new dataset

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": "4.32.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.32.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6331a66b16f3873706615f015a50396120b5237ee4750edc2a62cbfaad23e6
+size 503128704

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac529b967f0cedc888171d47a8d50ebcfb35489c72910a606cd3509252f03db
+size 1006355013

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf819235225ac6292688d212363484e39cce8958c0df294c3a3b18b985278ada
+size 14511

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93dc8e5adbcdf4d41a412913cda4e78a5512398dfddc9997def9051d55af16e1
+size 627

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "bos_token",
+    "eos_token",
+    "unk_token"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "bos_token",
+    "eos_token",
+    "unk_token"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8ccf6a934e3745c586125dc2b5d4deb819a3501a0380c3b61dee27a6a054c7
+size 4155