gpt3-small-2700steps

config.json

@@ -0,0 +1,28 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2Model"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 3,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "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,
+  "use_cache": true,
+  "vocab_size": 42000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e01921d4eb10a5a78aea2a9a636cb6f9197c6ab97dd95144d3c20ec008f6cb
+size 525899465

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c966ad883d6ac22302742844391f57189762c38f1af35d250ccd5659d9cea9
+size 475713872

tokenizer_config.json

@@ -0,0 +1,5 @@
+{
+  "do_lower_case": true,
+  "strip_accents": false,
+  "model_max_length": 2048
+}