added model

README.md

@@ -0,0 +1,56 @@
+---
+language: de
+
+widget:
+- text: "In einer schockierenden Entdeckung fanden Wissenschaftler eine Herde Einhörner, die in einem abgelegenen, zuvor unerforschten Tal in den Anden lebten."
+---
+
+# BPT2
+
+See the [GPT2 model card](https://huggingface.co/gpt2) for considerations on limitations and bias. See the [GPT2 documentation](https://huggingface.co/transformers/model_doc/gpt2.html) for details on GPT2.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("tursunali/bpt2")
+model = AutoModelForCausalLM.from_pretrained("tursunali/bpt2")
+
+prompt = "<your prompt>"
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+print(pipe(prompt)[0]["generated_text"])
+```
+
+Also, two tricks might improve the generated text:
+
+```python
+output = model.generate(
+    # during training an EOS token was used to mark the beginning of each text
+    # so it can help to insert it at the start
+    torch.tensor(
+        [tokenizer.eos_token_id] + tokenizer.encode(prompt)
+    ).unsqueeze(0),
+    do_sample=True,
+    # try setting bad_words_ids=[[0]] to disallow generating an EOS token, without this the model is
+    # prone to ending generation early because a significant number of texts from the training corpus
+    # is quite short
+    bad_words_ids=[[0]],
+    max_length=max_length,
+)[0]
+print(tokenizer.decode(output))
+```
+
+## Citing
+
+Please cite BPT2 as follows:
+
+```
+@misc{Backpacker_Trail_German_large_2022,
+author = {BackpackerTrail, Tursunali Kholdorov},
+title = {{BPT2: Backpacker Trail German versions of BPT2}},
+url = {https://github.com/bminixhofer/gerpt2},
+year = {2022}
+}
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e73b994389ab71c24f5b4de30f5898120340b4184da42b916f16b411c963a4
+size 3391352276

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}, "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "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}