First commit

README.md

@@ -0,0 +1,78 @@
+<!---
+# ##############################################################################################
+# 
+# Copyright (c) 2021-, NVIDIA CORPORATION.  All rights reserved.
+# 
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+# 
+#     http://www.apache.org/licenses/LICENSE-2.0
+# 
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# 
+# ##############################################################################################
+-->
+
+This is an archive of [nvidia/megatron-gpt2-345m](https://huggingface.co/nvidia/megatron-gpt2-345m) that contains readily available model weights (375M). Its performance on Wikitext-103 is 19.31.<sup>1</sup> In comparison, the performance of GPT2-large (1.5B) is 17.48 and GPT2-medium (762M) is 22.05.<sup>2</sup>
+
+### References
+
+1. Shoeybi, Mohammad, et al. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv, 2019, [https://doi.org/10.48550/ARXIV.1909.08053](https://doi.org/10.48550/ARXIV.1909.08053).
+2. Alec Radford, et al. Language Models are Unsupervised Multitask Learners. OpenAI, 2019. [https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf](https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf).
+
+## Description
+
+[Megatron](https://arxiv.org/pdf/1909.08053.pdf) is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA. This particular Megatron model was trained from a generative, left-to-right transformer in the style of GPT-2. This model was trained on text sourced from Wikipedia, RealNews, OpenWebText, and CC-Stories. It contains 345 million parameters. 
+
+Find more information at [https://github.com/NVIDIA/Megatron-LM](https://github.com/NVIDIA/Megatron-LM)
+
+# How to run Megatron GPT2 using Transformers
+
+## Text generation
+
+The following code shows how to use the Megatron GPT2 checkpoint and Transformers to generate text.
+
+```python
+import os
+import torch
+
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+model = GPT2LMHeadModel.from_pretrained("robowaifudev/megatron-gpt2-345m")
+
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+    model.to(device)
+    model.half()
+else:
+    device = torch.device("cpu")
+model.eval()
+
+# Generate
+text = "Hello world!"
+input_ids = tokenizer.encode(text, return_tensors="pt")
+output = model.generate(
+    input_ids=input_ids,
+    max_length=len(input_ids) + 32,
+    do_sample=True,
+    top_k=64,
+    top_p=0.9,
+    temperature=0.8,
+    num_return_sequences=1
+)
+
+# Output the text.
+for i, sentence in enumerate(output):
+    text = tokenizer.decode(sentence, clean_up_tokenization_spaces=True)
+    print(f"{i}:", text)
+```
+
+# Original code
+
+The original Megatron code can be found here: [https://github.com/NVIDIA/Megatron-LM](https://github.com/NVIDIA/Megatron-LM).

config.json

@@ -0,0 +1,82 @@
+{
+    "vocab_size": 50257,
+    "n_positions": 1024,
+    "n_embd": 1024,
+    "n_layer": 24,
+    "n_head": 16,
+    "n_inner": 4096,
+    "activation_function": "gelu_new",
+    "resid_pdrop": 0.1,
+    "embd_pdrop": 0.1,
+    "attn_pdrop": 0.1,
+    "layer_norm_epsilon": 1e-05,
+    "initializer_range": 0.02,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "scale_attn_weights": true,
+    "use_cache": true,
+    "scale_attn_by_inverse_layer_idx": false,
+    "reorder_and_upcast_attn": false,
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "use_bfloat16": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": true,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "chunk_size_feed_forward": 0,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "architectures": ["GPT2LMHeadModel"],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "pad_token_id": null,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "",
+    "transformers_version": "4.15.0",
+    "n_ctx": 1024,
+    "gradient_checkpointing": false,
+    "model_type": "gpt2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12fa6afe8f5a50cf32070b7d401a66916f549d587a22a0412e8b83c1f386a8c5
+size 735011993