Update README.md

README.md

@@ -6,25 +6,26 @@ license_link: >-
 ---
 ## Nemotron-4-340B-Instruct
 
-[![Model architectuve](https://img.shields.io/badge/Model%20Arch-Transformer%20Decoder-green)](#model-architecture)[![Model size](https://img.shields.io/badge/Params-340B-green)](#model-architecture)[![Language](https://img.shields.io/badge/Language-Multilingual-green)](#datasets)
+[![Model architecture](https://img.shields.io/badge/Model%20Arch-Transformer%20Decoder-green)](#model-architecture)[![Model size](https://img.shields.io/badge/Params-340B-green)](#model-architecture)[![Language](https://img.shields.io/badge/Language-Multilingual-green)](#datasets)
 
 ### Model Overview
 
-Nemotron-4-340B-Instruct is a large language model (LLM) that can be used as part of a synthetic data generation pipeline to create training data that helps researchers and developers build their own LLMs; and is a fine-tuned version of the Nemotron-4-340B-Base model, optimized for English single and multi-turn chat use-cases. The base model was pre-trained on a corpus of 9 trillion tokens consisting of a diverse assortment of English based texts,50+ natural languages, and 40+ coding languages. 
+Nemotron-4-340B-Instruct is a large language model (LLM) that can be used as part of a synthetic data generation pipeline to create training data that helps researchers and developers build their own LLMs. It is a fine-tuned version of the Nemotron-4-340B-Base model, optimized for English-based single and multi-turn chat use-cases. It supports a context length of 4,096 tokens. 
+
+The base model was pre-trained on a corpus of 9 trillion tokens consisting of a diverse assortment of English based texts, 50+ natural languages, and 40+ coding languages. Subsequently the Nemotron-4-340B-Instruct model went through additional alignment steps including:
 
-Subsequently the Nemotron-4-340B-Instruct model went through additional alignment steps including:
 - Supervised Fine-tuning (SFT)
 - Direct Preference Optimization (DPO)
-- Additional in-house alignment technique: Reward-aware Preference Optimization (RPO)
+- Reward-aware Preference Optimization (RPO) ([Additional in-house alignment technique](https://research.nvidia.com/publication/2024-06_nemotron-4-340b)) 
 
-Throughout the alignment process, we relied on only approximately 20K human-annotated data while our data generation pipeline synthesized over 98% of the data used for supervised fine-tuning and preference fine-tuning (DPO & RPO). We provide comprehensive details about our synthetic data generation pipeline in the technical report.
+Throughout the alignment process, we relied on only approximately 20K human-annotated data while our data generation pipeline synthesized over 98% of the data used for supervised fine-tuning and preference fine-tuning (DPO & RPO). We provide comprehensive details about our synthetic data generation pipeline in the [technical report](https://research.nvidia.com/publication/2024-06_nemotron-4-340b).
 
 This results in a model that is aligned for human chat preferences, improvements in mathematical reasoning, coding and instruction-following, and is capable of generating high quality synthetic data for a variety of use cases.
 
 Under the NVIDIA Open Model License, NVIDIA confirms: 
-- Models are commercially usable. 
-- You are free to create and distribute Derivative Models. 
-- NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models.
+Models are commercially usable. 
+You are free to create and distribute Derivative Models. 
+NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models.
 
 ### License: 
 
@@ -36,44 +37,75 @@ Nemotron-4-340B-Instruct is a chat model intended for use for the English langua
 
 Nemotron-4-340B-Instruct is designed for Synthetic Data Generation to enable developers and enterprises for building and customizing their own large language models and LLM applications. 
 
-The instruct model itself can be further customized using the [NeMo Framework](https://docs.nvidia.com/nemo-framework/index.html) suite of customization tools including Parameter-Efficient Fine-Tuning (P-tuning, Adapters, LoRA), and SFT/Steer-LM/RLHF using [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner).
+The instruct model itself can be further customized using the [NeMo Framework](https://docs.nvidia.com/nemo-framework/index.html) suite of customization tools including Parameter-Efficient Fine-Tuning (P-tuning, Adapters, LoRA, and more), and Model Alignment (SFT, SteerLM, RLHF, and more) using [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner).
 
 **Model Developer:** NVIDIA
 
-**Model Input:** Text
-**Input Format:**  String
-**Input Parameters:**  One-Dimensional (1D)
-
-**Model Output:** Text
-**Output Format:**  String
-**Output Parameters:**  1D
+**Model Dates:** Nemotron-4-340B-Instruct was trained between December 2023 and May 2024.
 
-**Model Dates:** Nemotron-4-340B-Instruct was trained between December 2023 and May 2024
-
-**Data Freshness:** The pretraining data has a cutoff of June 2023
+**Data Freshness:** The pretraining data has a cutoff of June 2023.
 
 ### Required Hardware
 
 BF16 Inference:
-- 8x H200 (1x H200 Node)
-- 16x H100 (2x H100 Nodes)
-- 16x A100 (2x A100 Nodes)
+- 8x H200 (1x H200 node)
+- 16x H100 (2x H100 nodes)
+- 16x A100 80GB (2x A100 80GB nodes)
 
-FP8 Inference:
-- 8x H100 (1x H100 Node)
 
 ### Model Architecture:
 
-Nemotron-4-340B-Base, is standard decoder-only Transformer, trained with a sequence length of 4096 tokens, uses Grouped-Query Attention (GQA), and Rotary Position Embeddings (RoPE).
+Nemotron-4-340B-Instruct is standard decoder-only Transformer, trained with a sequence length of 4096 tokens, uses Grouped-Query Attention (GQA), and Rotary Position Embeddings (RoPE).
 
 **Architecture Type:** Transformer Decoder (auto-regressive language model)
 
 **Network Architecture:**
 Nemotron-4
 
+### Prompt Format
+
+Note: For Nemotron-4-340B-Instruct we recommend keeping the system prompt empty.
+
+#### Single Turn
+
+```text
+<extra_id_0>System
+
+<extra_id_1>User
+{prompt}
+<extra_id_1>Assistant
+```
+
+#### Multi-Turn or Few-shot
+
+```text
+<extra_id_0>System
+
+<extra_id_1>User
+{prompt 1}
+<extra_id_1>Assistant
+{response 1}
+<extra_id_1>User
+{prompt 2}
+<extra_id_1>Assistant
+{response 2}
+...
+<extra_id_1>User
+{prompt N}
+<extra_id_1>Assistant
+```
+
+An example of a formattable prompt template is available in the following section.
+
 ### Usage
 
-1. We will spin up an inference server and then call the inference server in a python script. Let’s first define the python script ``call_server.py``
+Deployment and inference with Nemotron-4-340B-Instruct can be done in three steps using NeMo Framework:
+
+Create a Python script to interact with the deployed model.
+Create a Bash script to start the inference server
+Schedule a Slurm job to distribute the model across 4 nodes and associate them with the inference server.
+
+1. Define the Python script ``call_server.py``
 
 ```python
 import json
@@ -117,13 +149,13 @@ print(prompt)
 response = get_generation(prompt, greedy=True, add_BOS=False, token_to_gen=1024, min_tokens=1, temp=1.0, top_p=1.0, top_k=0, repetition=1.0, batch=False)
 response = response[len(prompt):]
 if response.endswith("<extra_id_1>"):
-	response = response[:-len("<extra_id_1>")]
+    response = response[:-len("<extra_id_1>")]
 print(response)
 ```
 
-2. Given this python script, we will create a bash script, which spins up the inference server within the NeMo container (```docker pull nvcr.io/nvidia/nemo:24.01.framework```) and calls the python script ``call_server.py``. The bash script ``nemo_inference.sh`` is as follows,
+2. Given this Python script, create a Bash script which spins up the inference server within the [NeMo container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo) (docker pull nvcr.io/nvidia/nemo:24.01.framework) and calls the Python script ``call_server.py``. The Bash script ``nemo_inference.sh`` is as follows,
 
-```bash
+```
 NEMO_FILE=$1
 WEB_PORT=1424
 
@@ -141,6 +173,7 @@ depends_on () {
 }
 
 
+
 /usr/bin/python3 /opt/NeMo/examples/nlp/language_modeling/megatron_gpt_eval.py \
         gpt_model_file=$NEMO_FILE \
         pipeline_model_parallel_split_rank=0 \
@@ -170,13 +203,13 @@ depends_on () {
 ```
 
 
-3. We can launch the ``nemo_inferece.sh`` with a slurm script defined like below, which starts a 2-node job for the model inference.
+3, Launch ``nemo_inference.sh`` with a Slurm script defined like below, which starts a 4-node job for model inference.
 
-```bash
+```
 #!/bin/bash
 #SBATCH -A SLURM-ACCOUNT
 #SBATCH -p SLURM-PARITION
-#SBATCH -N 2
+#SBATCH -N 2 # number of nodes
 #SBATCH -J generation      
 #SBATCH --ntasks-per-node=8   
 #SBATCH --gpus-per-node=8
@@ -186,7 +219,6 @@ RESULTS=<PATH_TO_YOUR_SCRIPTS_FOLDER>
 OUTFILE="${RESULTS}/slurm-%j-%n.out"
 ERRFILE="${RESULTS}/error-%j-%n.out"
 MODEL=<PATH_TO>/Nemotron-4-340B-Instruct
-CONTAINER="nvcr.io/nvidia/nemo:24.01.framework"
 
 MOUNTS="--container-mounts=<PATH_TO_YOUR_SCRIPTS_FOLDER>:/scripts,MODEL:/model"
 read -r -d '' cmd <<EOF
@@ -200,13 +232,10 @@ srun -o $OUTFILE -e $ERRFILE --container-image="$CONTAINER" $MOUNTS bash -c "${c
 
 #### MT-Bench (GPT-4-Turbo)
 
-Evaluated using MT-Bench judging by GPT-4-Turbo as described in the [HelpSteer2 Dataset Paper](https://arxiv.org/abs/2406.08673).
+Evaluated using MT-Bench judging by GPT-4-0125-Preview as described in Appendix H in the [HelpSteer2 Dataset Paper](https://arxiv.org/abs/2406.08673)
 
-Please note that these numbers aren't comparable with original MT-bench as we corrected [some references](https://github.com/lm-sys/FastChat/pull/3158)
-
-
-| total | writing |	roleplay | extraction |	stem | humanities | reasoning |	math | coding | turn 1 | turn 2 |
-| ----- | ------- | -------- | ---------- | ---- | ---------- | --------- | ---- | ------ | ------ | ------ | 
+| total | writing | roleplay | extraction | stem | humanities | reasoning | math | coding | turn 1 | turn 2 |
+| :----- | :------- | :-------- | :---------- | :---- | :---------- | :--------- | :---- | ------ | :------ | :------ | 
 | 8.22 | 8.70 | 8.70  | 9.20 | 8.75 | 8.95 | 6.40 | 8.40 | 6.70 | 8.61 | 7.84 | 
 
 #### IFEval
@@ -214,7 +243,7 @@ Please note that these numbers aren't comparable with original MT-bench as we co
 Evaluated using the Instruction Following Eval (IFEval) introduced in [Instruction-Following Evaluation for Large Language Models](https://arxiv.org/pdf/2311.07911).
 
 | Prompt-Strict Acc | Instruction-Strict Acc |
-| ----------------------- | ---------------------------- |
+| :----------------------- | :---------------------------- |
 | 79.9 | 86.1 |
 
 #### MMLU
@@ -222,7 +251,7 @@ Evaluated using the Instruction Following Eval (IFEval) introduced in [Instructi
 Evaluated using the Multi-task Language Understanding benchmarks as introduced in [Measuring Massive Multitask Language Understanding](https://arxiv.org/pdf/2009.03300)
 
 |MMLU 0-shot |
-| ----------------- |
+| :----------------- |
 | 78.7  | 
 
 #### GSM8K
@@ -230,7 +259,7 @@ Evaluated using the Multi-task Language Understanding benchmarks as introduced i
 Evaluated using the Grade School Math 8K (GSM8K) benchmark as introduced in [Training Verifiers to Solve Math Word Problems](https://arxiv.org/pdf/2110.14168v2).
 
 | GSM8K 0-shot |
-| ----------------- | 
+| :----------------- | 
 | 92.3 | 
 
 #### HumanEval
@@ -239,7 +268,7 @@ Evaluated using the HumanEval benchmark as introduced in [Evaluating Large Langu
 
 
 | HumanEval 0-shot |
-| ----- |
+| :----- |
 | 73.2 |
 
 #### MBPP
@@ -247,7 +276,7 @@ Evaluated using the HumanEval benchmark as introduced in [Evaluating Large Langu
 Evaluated using the MBPP Dataset as introduced in the [Program Synthesis with Large Language Models](https://arxiv.org/abs/2108.07732) paper.
 
 | MBPP 0-shot|
-| ----------------- | 
+| :----------------- | 
 | 75.4 | 
 
 
@@ -256,7 +285,7 @@ Evaluated using the MBPP Dataset as introduced in the [Program Synthesis with La
 Evaluated using the [Arena-Hard Pipeline](https://lmsys.org/blog/2024-04-19-arena-hard/) from the LMSys Org.
 
 | Arena Hard |
-| ----------------- | 
+| :----------------- | 
 | 54.2 | 
 
 #### AlpacaEval 2.0 LC
@@ -264,7 +293,7 @@ Evaluated using the [Arena-Hard Pipeline](https://lmsys.org/blog/2024-04-19-aren
 Evaluated using the AlpacaEval 2.0 LC (Length Controlled) as introduced in the paper: [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://arxiv.org/abs/2404.04475)
 
 | AlpacaEval 2.0 LC|
-| ----------------- | 
+| :----------------- | 
 | 41.5 | 
 
 
@@ -273,18 +302,22 @@ Evaluated using the AlpacaEval 2.0 LC (Length Controlled) as introduced in the p
 Evaluated using the CantTalkAboutThis Dataset as introduced in the [CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues](https://arxiv.org/abs/2404.03820) paper.
 
 | Distractor F1 | On-topic F1 |
-| ----------------------- | ---------------------------- |
+| :----------------------- | :---------------------------- |
 | 81.7  | 97.7 |
 
 
 ### Adversarial Testing and Red Teaming Efforts 
 
 The Nemotron-4 340B-Instruct model underwent extensive safety evaluation including adversarial testing via three distinct methods: 
-- [Garak](https://docs.garak.ai/garak), is an automated LLM vulnerability scanner that probes for common weaknesses, including prompt injection and data leakage. 
-- [AEGIS](https://arxiv.org/pdf/2404.05993), is a content safety evaluation dataset and LLM based content safety classifier model, that adheres to a broad taxonomy of 13 categories of critical risks in human-LLM interactions.
-- Human Content Red Teaming leveraging human interaction and evaluation of the models' responses.
+[Garak](https://docs.garak.ai/garak), is an automated LLM vulnerability scanner that probes for common weaknesses, including prompt injection and data leakage. 
+[AEGIS](https://arxiv.org/pdf/2404.05993), is a content safety evaluation dataset and LLM based content safety classifier model, that adheres to a broad taxonomy of 13 categories of critical risks in human-LLM interactions.
+Human Content Red Teaming leveraging human interaction and evaluation of the models' responses.
+
+### 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.  For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards [Insert Link to Model Card++ here].  Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
+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.  For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards [here](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/nemotron-4-340b-instruct).  Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).