Upload folder using huggingface_hub

README.md

@@ -0,0 +1,22 @@
+# Decoder Language Model
+Ein kleiner autoregressiver Decoder-only Transformer, trainiert auf Tiny Shakespeare.
+
+## Architektur
+- d_model=128, num_layers=2, nhead=4
+- ~500k Parameter
+
+## Metriken
+- Loss (Train): 0.6342
+- Perplexity (Train): 1.8854
+
+## Laden
+```python
+from transformers import GPT2Tokenizer
+import torch
+from model import DecoderLanguageModel
+
+tokenizer = GPT2Tokenizer.from_pretrained("ahmadisakina/decoder-language-model")
+model = DecoderLanguageModel(vocab_size=tokenizer.vocab_size, d_model=128, nhead=4, num_layers=2)
+model.load_state_dict(torch.load("pytorch_model.bin"))
+model.eval()
+```

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647ea898e93e4de01b2617349641fa2923d83208a66055a1a29ba73de07ca4b5
+size 53847487

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}