first sft model version

README.md

@@ -1,3 +1,6 @@
 ---
 license: apache-2.0
 ---
+# GPT-2 Large Model for OpenAI TLDR Summarization
+
+SFT model

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50259,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50257,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "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": false,
+      "max_length": 256
+    }
+  },
+  "vocab_size": 50261
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d04b240e723f5624e0784001d6c75e303661305a89883a8f5a47a64088e915
+size 1585889415