Update README.md

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 nemo/*.nemo filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

NOTICE

@@ -0,0 +1,3 @@
+Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ 
+NVIDIA CORPORATION, its affiliates and licensors retain all intellectual property and proprietary rights in and to this material, related documentation and any modifications thereto. Any use, reproduction, disclosure or distribution of this material and related documentation without an express license agreement from NVIDIA CORPORATION or its affiliates is strictly prohibited.

README.md

@@ -1,90 +1,150 @@
----
-license: other
-license_name: nvidia-open-model-license
-license_link: >-
-  https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
----
-
-# Minitron 8B Base
-
-Minitron is a family of small language models (SLMs) obtained by pruning NVIDIA's [Nemotron-4 15B](https://arxiv.org/abs/2402.16819) model. We prune model embedding size, attention heads, and MLP intermediate dimension, following which, we perform continued training with distillation to arrive at the final models.
-
-Deriving the Minitron 8B and 4B models from the base 15B model using our approach requires up to **40x fewer training tokens** per model compared to training from scratch; this results in **compute cost savings of 1.8x** for training the full model family (15B, 8B, and 4B). Minitron models exhibit up to a 16% improvement in MMLU scores compared to training from scratch, perform comparably to other community models such as Mistral 7B, Gemma 7B and Llama-3 8B, and outperform state-of-the-art compression techniques from the literature. Please refer to our [arXiv paper](https://arxiv.org/abs/2407.14679) for more details.
-
-Minitron models are for research and development only.
-
-## HuggingFace Quickstart
-
-The [PR](https://github.com/huggingface/transformers/pull/31699) to support our models in Hugging Face in under review and expected to be merged soon. In the meantime, this [branch](https://github.com/suiyoubi/transformers/tree/aot/nemotron-support) at [commit ID 63d9cb0](https://github.com/suiyoubi/transformers/commit/63d9cb0afd2bf5d4cb5431ba1b2c4e353752a937) can be used for Minitron models:
-
-```
-git clone git@github.com:suiyoubi/transformers.git
-cd transformers
-git checkout 63d9cb0
-pip install .
-```
-The following code provides an example of how to load the Minitron-8B model and use it to perform text generation.
-
-```python
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-# Load the tokenizer and model
-model_path = "nvidia/Minitron-8B-Base"
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-
-device='cuda'
-dtype=torch.bfloat16
-model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device)
-
-# Prepare the input text
-prompt = "To be or not to be,"
-input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
-
-# Generate the output
-output_ids = model.generate(input_ids, max_length=50, num_return_sequences=1)
-
-# Decode and print the output
-output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
-print(output_text)
-```
-
-## License
-
-Minitron is released under the [NVIDIA Open Model License Agreement](https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf).
-
-## Evaluation Results
-
-*5-shot performance.* Language Understanding evaluated using [Massive Multitask Language Understanding](https://arxiv.org/abs/2009.03300):
-
-| Average |
-| :---- |
-| 63.8 |
-
-*Zero-shot performance.* Evaluated using select datasets from the [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) with additions:
-
-HellaSwag | Winogrande | GSM8K| ARC-C | XLSum |
-| :------------- | :------------- | :------------- | :------------- | :------------- |
-| 80.7 | 79.0 | 51.3  | 52.6 | 31.2
-
-
-*Code generation performance*. Evaluated using [HumanEval](https://github.com/openai/human-eval):
-
-| p@1, 0-Shot |
-| :------------- |
-| 31.6 |
-
-Please refer to our [paper](https://arxiv.org/abs/2407.14679) for the full set of results.
-
-## Citation
-
-If you find our work helpful, please consider citing our paper:
-```
-@article{minitron2024,
-      title={Compact Language Models via Pruning and Knowledge Distillation}, 
-      author={Saurav Muralidharan and Sharath Turuvekere Sreenivas and Raviraj Joshi and Marcin Chochowski and Mostofa Patwary and Mohammad Shoeybi and Bryan Catanzaro and Jan Kautz and Pavlo Molchanov},
-      journal={arXiv preprint arXiv:2407.14679},
-      year={2024},
-      url={https://arxiv.org/abs/2407.14679}, 
-}
-```
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: >-
+  https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
+library_name: transformers
+pipeline_tag: text-generation
+language:
+  - en
+tags:
+  - nvidia
+  - llama-3
+  - pytorch  
+---
+# Model Overview
+
+Minitron-8B-Base is a large language model (LLM) obtained by pruning Nemotron-4 15B; specifically, we prune model embedding size, number of attention heads, and MLP intermediate dimension. Following pruning, we perform continued training with distillation using 94 billion tokens to arrive at the final model; we use the continuous pre-training data corpus used in Nemotron-4 15B for this purpose.
+
+Deriving the Minitron 8B and 4B models from the base 15B model using our approach requires up to **40x fewer training tokens** per model compared to training from scratch; this results in **compute cost savings of 1.8x** for training the full model family (15B, 8B, and 4B). Minitron models exhibit up to a 16% improvement in MMLU scores compared to training from scratch, perform comparably to other community models such as Mistral 7B, Gemma 7B and Llama-3 8B, and outperform state-of-the-art compression techniques from the literature. Please refer to our [arXiv paper](https://arxiv.org/abs/2407.14679) for more details.
+
+This model is for research and development only.
+
+**Model Developer:** NVIDIA 
+
+**Model Dates:** Minitron-8B-Base was trained between February 2024 and June 2024.
+
+## License
+
+Minitron-8B-Base is released under the [NVIDIA Open Model License Agreement](https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf).
+
+## Model Architecture
+
+Minitron-8B-Base uses a model embedding size of 4096, 48 attention heads, and an MLP intermediate dimension of 16384.
+It also uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE). 
+
+**Architecture Type:** Transformer Decoder (auto-regressive language model) 
+
+**Network Architecture:** Nemotron-4 
+
+**Input Type:** Text
+
+**Input Format:** String
+
+**Input Parameters:** None
+
+**Other Properties Related to Input:** None
+
+**Output Type:** Text
+
+**Output Format:** String
+
+**Output Parameters:** None
+
+**Other Properties Related to Output:** None
+
+## Usage
+
+Support for this model will be added in the upcoming `transformers` release. In the meantime, please install the library from source:
+
+```
+pip install git+https://github.com/huggingface/transformers
+```
+
+The following code provides an example of how to load the Minitron-8B model and use it to perform text generation.
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the tokenizer and model
+model_path = "nvidia/Minitron-8B-Base"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+device='cuda'
+dtype=torch.bfloat16
+model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device)
+
+# Prepare the input text
+prompt = "To be or not to be,"
+input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
+
+# Generate the output
+output_ids = model.generate(input_ids, max_length=50, num_return_sequences=1)
+
+# Decode and print the output
+output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(output_text)
+```
+
+## Dataset & Training
+
+**Data Collection Method:** Hybrid
+
+**Labeling Method:** Not Applicable
+
+**Properties:** The training corpus for Minitron-8B-Base consists of English and multilingual text, as well as code. Our sources cover a variety of document types such as: webpages, dialogue, articles, and other written materials. The corpus spans domains including legal, math, science, finance, and more. In our continued training set, we introduce a small portion of question-answering, and alignment style data to improve model performance. 
+
+**Data Freshness:** The pretraining data has a cutoff of June 2023. 
+
+## Evaluation Results
+
+*5-shot performance.* Language Understanding evaluated using [Massive Multitask Language Understanding](https://arxiv.org/abs/2009.03300):
+
+| Average |
+| :---- |
+| 64.5 |
+
+*Zero-shot performance.* Evaluated using select datasets from the [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) with additions:
+
+HellaSwag | Winogrande | GSM8K| ARC-C | XLSum |
+| :------------- | :------------- | :------------- | :------------- | :------------- |
+| 81.6 | 80.3 | 54.2  | 49.2 | 31.1
+
+
+*Code generation performance*. Evaluated using [HumanEval](https://github.com/openai/human-eval):
+
+| p@1, 0-Shot |
+| :------------- |
+| 31.6 |
+
+Please refer to our [paper](https://arxiv.org/abs/2407.14679) for the full set of results.
+
+## Inference
+**Engine:** TensorRT-LLM
+
+**Test Hardware:** NVIDIA A100
+
+**DType:** Float16/BFloat16
+
+## Limitations 
+
+The model was trained on data that contains toxic language, unsafe content, and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. 
+
+## Ethical Considerations 
+
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). 
+
+
+## Citation
+
+If you find our work helpful, please consider citing our paper:
+```
+@article{minitron2024,
+      title={Compact Language Models via Pruning and Knowledge Distillation}, 
+      author={Saurav Muralidharan and Sharath Turuvekere Sreenivas and Raviraj Joshi and Marcin Chochowski and Mostofa Patwary and Mohammad Shoeybi and Bryan Catanzaro and Jan Kautz and Pavlo Molchanov},
+      journal={arXiv preprint arXiv:2407.14679},
+      year={2024},
+      url={https://arxiv.org/abs/2407.14679}, 
+}
+```

config.json

@@ -13,15 +13,14 @@
   "model_type": "nemotron",
   "num_attention_heads": 48,
   "num_hidden_layers": 32,
-  "kv_channels": 128,
   "num_key_value_heads": 8,
   "norm_eps": 1e-05,
   "rope_theta": 10000,
-  "rope_percent": 0.5,
-  "rope_scaling": null,
+  "partial_rotary_factor": 0.5,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.32.0.dev0",
+  "transformers_version": "4.44.0",
   "use_cache": true,
-  "vocab_size": 256000
-}
+  "vocab_size": 256000,
+  "head_dim": 128
+}

nemo/minitron-8b-base.nemo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:135cb73e323b91a3830e60d8d5a5bef066a0c15885935756de6ccb34d60b2809
+oid sha256:59162ca3471a17052c78518402342477d81650f3b6bc8c87fb37dec5a35c904a
 size 16554813440

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0c84c2ed78c94d103bbf81f4205206a8e022e0c7c1135c693e7574535fa470
+oid sha256:debb954a1720801fa4c054f0c761fe344758ef659419d45e5b9a5e7b10722a11
 size 16543512498

special_tokens_map.json

@@ -1,23 +1,4 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>"
 }

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d0648daa0467fb02ddef7ff25460321dab2fbb20c280ae0bc1ea8052f7df90
+size 18143149