first version

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_fast",
+  "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_embd": 768,
+  "n_head": 16,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "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,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 60032
+}

model_optim_rng.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92c16bdda192a17dc49f2f7bd4faf623059a55ef4312890632de5c0eea358c5
+size 263946713

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac203dc7950d0db275982784a5c6bd7b2062ba96af2952ff1b11fdf4aff53c3
+size 289111721

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<BOS>",
+  "cls_token": "<BOS>",
+  "eos_token": "<EOS>",
+  "pad_token": "<PAD>",
+  "sep_token": "<EOS>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token": "<BOS>",
+  "cls_token": "<BOS>",
+  "eos_token": "<EOS>",
+  "name_or_path": "/home/mulcar/bigscience/gpt3-sl-tok-large.60k-bytelevel",
+  "pad_token": "<PAD>",
+  "sep_token": "<EOS>",
+  "special_tokens_map_file": "/home/mulcar/bigscience/gpt3-sl-tok-large.60k-bytelevel/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "model_max_length": 1024
+}