GPT-2 Large

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tf_model.h5 filter=lfs diff=lfs merge=lfs -text
+config.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,38 +1,3 @@
-{
-  "_name_or_path": "gpt2-large",
-  "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,
-  "initializer_range": 0.02,
-  "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,
-  "output_attentions": 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": 50
-    }
-  },
-  "transformers_version": "4.8.1",
-  "use_cache": true,
-  "vocab_size": 50257
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:364655f02df5d1801be741b988e8917db45ded8da2230c849857a5a3c2f51da1
+size 869

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb894e748ca33b2f5bee99d2cd7af98895fdf0e433fb9c1ec690e3d5ecd68a72
+size 3096618024