init

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,36 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "rotary_dim": 64,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.12.0.dev0",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "temperature": 1.0,
+      "max_length": 128
+    }
+  },
+  "torch_dtype": "float32",
+  "use_cache": true,
+  "vocab_size": 64512
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211b2bf7b4561ddd83a6d6321e726455847041af7c3bb2ae5b6925ac832d3ae7
+size 24670302149

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[BOS]", "eos_token": "[EOS]", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "[BOS]", "eos_token": "[EOS]", "unk_token": "[UNK]", "pad_token": "[PAD]", "special_tokens_map_file": null, "name_or_path": "/home/curtiskim/curtis_dev/mesh-transformer-jax/tokenizer/v1.5_b/", "tokenizer_class": "PreTrainedTokenizerFast"}