Adding model

README.md

@@ -1,3 +1,15 @@
 ---
+language:
+- is
 license: cc-by-4.0
+datasets:
+- igc
 ---
+
+# Icelandic GPT-2 model
+This Icelandic GPT-2 language model was pretrained on the [Icelandic Gigaword Corpus](http://igc.arnastofnun.is/) (IGC, 2020 version), which contains approximately 1.532 million running words. The model was trained for 20 epochs on a TPU v3-8, with a total training time of 3 days and 21 hours. The hyperparameters used for training can be found in the [JAX/Flax documentation](https://github.com/huggingface/transformers/tree/main/examples/flax/language-modeling#train-model-1) for the Transformers library. The model uses a byte-level BPE tokenizer with a vocabulary size of 51,000.
+
+**Note**: This model was pretrained on a tokenized and sentence-segmentized version of the IGC, which is reflected by the generated text. A new version of this model, trained on a pre-tokenized version of IGC (2022 version), is forthcoming.
+
+# Acknowledgments
+This research was supported with Cloud TPUs from Google's TPU Research Cloud (TRC).

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "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": 0.0,
+  "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": "4.17.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51000
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2dbccf2e3ec779ab56e2912bfdefc0aa7178c392ef3fc1f5c33c9a8ce0bab83
+size 500046616

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9089b8874a22f0e727485b8f078fe6df0ad94f2033de12365827dfb255a388
+size 512683881

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512, "special_tokens_map_file": null, "tokenizer_class": "GPT2Tokenizer"}