初始化项目，由ModelHub XC社区提供模型

Model: Pyjay/gpt2-medium-dutch-finetuned-text-generation
Source: Original Platform

.gitattributes

@@ -0,0 +1,17 @@
+*.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
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,60 @@
+---
+tags:
+- generated_from_trainer
+model_index:
+- name: gpt2-medium-dutch-finetuned-text-generation
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gpt2-medium-dutch-finetuned-text-generation
+
+This model is a fine-tuned version of [GroNLP/gpt2-medium-dutch-embeddings](https://huggingface.co/GroNLP/gpt2-medium-dutch-embeddings) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.9268
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 394  | 4.0144          |
+| 3.3633        | 2.0   | 788  | 3.9379          |
+| 2.7108        | 3.0   | 1182 | 3.9268          |
+
+
+### Framework versions
+
+- Transformers 4.9.0
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "GroNLP/gpt2-medium-dutch-embeddings",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "pad_token_id": 0,
+  "predict_special_tokens": true,
+  "resid_pdrop": 0.1,
+  "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": 100,
+      "no_repeat_ngram_size": 4,
+      "num_beams": 10,
+      "repetition_penalty": 10.0,
+      "temperature": 2.0,
+      "top_k": 20,
+      "top_p": 0.9
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0",
+  "use_cache": true,
+  "vocab_size": 40000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02576a16d66d8bc6e100c5b4fdeffac9793f7c28d9d451c94ee05b23e23914e6
+size 1402568665

runs/Jul22_07-09-09_262749f64873/1626937783.167601/events.out.tfevents.1626937783.262749f64873.367.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb38d660d447e535b0b41ecb45103cef220178877ff5a4010efe581d7af63717
+size 4207

runs/Jul22_07-09-09_262749f64873/events.out.tfevents.1626937783.262749f64873.367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d48ec84d9aff7e71af48613dc7a8da7507739051e2c04a7543e77ecc3ed01b
+size 4895

runs/Jul22_07-09-09_262749f64873/events.out.tfevents.1626938455.262749f64873.367.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6f9053687026839de53e2cba553f0ac4d126d4c54dd10eb8866e279365aae3
+size 311

runs/Jul22_13-26-00_cca08a2870a8/1626960423.1561673/events.out.tfevents.1626960423.cca08a2870a8.77.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0162390f811d7e508fe7be2136d754102074681dc6e8f1bdefda55a49c8385a0
+size 4204

runs/Jul22_13-26-00_cca08a2870a8/events.out.tfevents.1626960423.cca08a2870a8.77.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65aad11a11054c48943f021d3bb38dd1ec2cd75de0b6261b2e3e1e2437f208f2
+size 5210

runs/Jul22_13-26-00_cca08a2870a8/events.out.tfevents.1626961740.cca08a2870a8.77.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947d4f0cdfb66aad5ddef9e56e219b36f10d8ef62f4d6bad3bd44d97ab4d1c96
+size 311

runs/Jul22_14-08-16_cca08a2870a8/1626962900.2511847/events.out.tfevents.1626962900.cca08a2870a8.77.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da6367fcff1eab9d607fb96ba57923b96c322e367ffe934dc6f6cd7325f9650
+size 4204

runs/Jul22_14-08-16_cca08a2870a8/events.out.tfevents.1626962900.cca08a2870a8.77.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea6150cc106611f9ab66ba60a461f7f863b0ae6937a62c4573823c68efe1925
+size 5681

runs/Jul22_14-08-16_cca08a2870a8/events.out.tfevents.1626964912.cca08a2870a8.77.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2932d6b31ce9264e36c199a886f32e959ce7be5ea1d2c74bc1ac43f58b15b559
+size 311

runs/Jul23_09-31-57_c12069dbbd38/1627032790.6594548/events.out.tfevents.1627032790.c12069dbbd38.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d535a121a4790c88533da76b2b24874f520dbe3df355cf4ccde1645905f4fad9
+size 4204

runs/Jul23_09-31-57_c12069dbbd38/events.out.tfevents.1627032790.c12069dbbd38.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6cdd8f94824ff06ac362bd5acfef7706054ce7d2bbbf04de8a785603fecca7e
+size 4896

runs/Jul23_09-31-57_c12069dbbd38/events.out.tfevents.1627033449.c12069dbbd38.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf64d3fe44f9bd139c0ff560e951d4d97c38976647894b2ab838a8714f75cc23
+size 311

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "special_tokens_map_file": "/root/.cache/huggingface/transformers/eea55dc204333a37c9f45d89c1052c0a9d63e06b9436506032d8242ad5e6df36.78b6ed69c656c44d9052f32c25d283e88026750a6f2b9eda91648840c84ef783", "name_or_path": "GroNLP/gpt2-medium-dutch-embeddings", "tokenizer_class": "GPT2Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfab0de179c723884484c8dd55a86c2587f0c6b71ec5117a7cfd173dc4b43e7
+size 2671