Initial commit

1684810426.2644649/events.out.tfevents.1684810426.dacc681f8195.328.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f610a8fa414d6f6a6adb4f5c917f318d8f90737a31e20057baa7a20461a60807
+size 5875

1684810426.2644649/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.0.dev0"
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "BigSalmon/InstructGPT2Large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "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": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

events.out.tfevents.1684810426.dacc681f8195.328.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb0b45cfde106dd709535be879a33a75cd87144c19fb0c8b31743e79ee96944
+size 5098

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7155311b6b2c96eae9e71ad43e132947d90c46c2d54279056ac625e6a9de3830
+size 3096262685

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40f34ae2aa7df12d3c9fe2deb5e372c9c85df950d57b5eeb94ccf92d315cf91
+size 3835