Alternatives to NVIDIA NeMo Megatron
Compare NVIDIA NeMo Megatron alternatives for your business or organization using the curated list below. SourceForge ranks the best alternatives to NVIDIA NeMo Megatron in 2025. Compare features, ratings, user reviews, pricing, and more from NVIDIA NeMo Megatron competitors and alternatives in order to make an informed decision for your business.
-
1
Vertex AI
Google
Build, deploy, and scale machine learning (ML) models faster, with fully managed ML tools for any use case. Through Vertex AI Workbench, Vertex AI is natively integrated with BigQuery, Dataproc, and Spark. You can use BigQuery ML to create and execute machine learning models in BigQuery using standard SQL queries on existing business intelligence tools and spreadsheets, or you can export datasets from BigQuery directly into Vertex AI Workbench and run your models from there. Use Vertex Data Labeling to generate highly accurate labels for your data collection. Vertex AI Agent Builder enables developers to create and deploy enterprise-grade generative AI applications. It offers both no-code and code-first approaches, allowing users to build AI agents using natural language instructions or by leveraging frameworks like LangChain and LlamaIndex. -
2
Cerebras-GPT
Cerebras
State-of-the-art language models are extremely challenging to train; they require huge compute budgets, complex distributed compute techniques and deep ML expertise. As a result, few organizations train large language models (LLMs) from scratch. And increasingly those that have the resources and expertise are not open sourcing the results, marking a significant change from even a few months back. At Cerebras, we believe in fostering open access to the most advanced models. With this in mind, we are proud to announce the release to the open source community of Cerebras-GPT, a family of seven GPT models ranging from 111 million to 13 billion parameters. Trained using the Chinchilla formula, these models provide the highest accuracy for a given compute budget. Cerebras-GPT has faster training times, lower training costs, and consumes less energy than any publicly available model to date.Starting Price: Free -
3
Megatron-Turing
NVIDIA
Megatron-Turing Natural Language Generation model (MT-NLG), is the largest and the most powerful monolithic transformer English language model with 530 billion parameters. This 105-layer, transformer-based MT-NLG improves upon the prior state-of-the-art models in zero-, one-, and few-shot settings. It demonstrates unmatched accuracy in a broad set of natural language tasks such as, Completion prediction, Reading comprehension, Commonsense reasoning, Natural language inferences, Word sense disambiguation, etc. With the intent of accelerating research on the largest English language model till date and enabling customers to experiment, employ and apply such a large language model on downstream language tasks - NVIDIA is pleased to announce an Early Access program for its managed API service to MT-NLG mode. -
4
NVIDIA NeMo
NVIDIA
NVIDIA NeMo LLM is a service that provides a fast path to customizing and using large language models trained on several frameworks. Developers can deploy enterprise AI applications using NeMo LLM on private and public clouds. They can also experience Megatron 530B—one of the largest language models—through the cloud API or experiment via the LLM service. Customize your choice of various NVIDIA or community-developed models that work best for your AI applications. Within minutes to hours, get better responses by providing context for specific use cases using prompt learning techniques. Leverage the power of NVIDIA Megatron 530B, one of the largest language models, through the NeMo LLM Service or the cloud API. Take advantage of models for drug discovery, including in the cloud API and NVIDIA BioNeMo framework. -
5
GPT-NeoX
EleutherAI
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library. This repository records EleutherAI's library for training large-scale language models on GPUs. Our current framework is based on NVIDIA's Megatron Language Model and has been augmented with techniques from DeepSpeed as well as some novel optimizations. We aim to make this repo a centralized and accessible place to gather techniques for training large-scale autoregressive language models, and accelerate research into large-scale training.Starting Price: Free -
6
Mistral NeMo
Mistral AI
Mistral NeMo, our new best small model. A state-of-the-art 12B model with 128k context length, and released under the Apache 2.0 license. Mistral NeMo is a 12B model built in collaboration with NVIDIA. Mistral NeMo offers a large context window of up to 128k tokens. Its reasoning, world knowledge, and coding accuracy are state-of-the-art in its size category. As it relies on standard architecture, Mistral NeMo is easy to use and a drop-in replacement in any system using Mistral 7B. We have released pre-trained base and instruction-tuned checkpoints under the Apache 2.0 license to promote adoption for researchers and enterprises. Mistral NeMo was trained with quantization awareness, enabling FP8 inference without any performance loss. The model is designed for global, multilingual applications. It is trained on function calling and has a large context window. Compared to Mistral 7B, it is much better at following precise instructions, reasoning, and handling multi-turn conversations.Starting Price: Free -
7
NLP Cloud
NLP Cloud
Fast and accurate AI models suited for production. Highly-available inference API leveraging the most advanced NVIDIA GPUs. We selected the best open-source natural language processing (NLP) models from the community and deployed them for you. Fine-tune your own models - including GPT-J - or upload your in-house custom models, and deploy them easily to production. Upload or Train/Fine-Tune your own AI models - including GPT-J - from your dashboard, and use them straight away in production without worrying about deployment considerations like RAM usage, high-availability, scalability... You can upload and deploy as many models as you want to production.Starting Price: $29 per month -
8
Azure OpenAI Service
Microsoft
Apply advanced coding and language models to a variety of use cases. Leverage large-scale, generative AI models with deep understandings of language and code to enable new reasoning and comprehension capabilities for building cutting-edge applications. Apply these coding and language models to a variety of use cases, such as writing assistance, code generation, and reasoning over data. Detect and mitigate harmful use with built-in responsible AI and access enterprise-grade Azure security. Gain access to generative models that have been pretrained with trillions of words. Apply them to new scenarios including language, code, reasoning, inferencing, and comprehension. Customize generative models with labeled data for your specific scenario using a simple REST API. Fine-tune your model's hyperparameters to increase accuracy of outputs. Use the few-shot learning capability to provide the API with examples and achieve more relevant results.Starting Price: $0.0004 per 1000 tokens -
9
Mistral Small 3.1
Mistral
Mistral Small 3.1 is a state-of-the-art, multimodal, and multilingual AI model released under the Apache 2.0 license. Building upon Mistral Small 3, this enhanced version offers improved text performance, and advanced multimodal understanding, and supports an expanded context window of up to 128,000 tokens. It outperforms comparable models like Gemma 3 and GPT-4o Mini, delivering inference speeds of 150 tokens per second. Designed for versatility, Mistral Small 3.1 excels in tasks such as instruction following, conversational assistance, image understanding, and function calling, making it suitable for both enterprise and consumer-grade AI applications. Its lightweight architecture allows it to run efficiently on a single RTX 4090 or a Mac with 32GB RAM, facilitating on-device deployments. It is available for download on Hugging Face, accessible via Mistral AI's developer playground, and integrated into platforms like Google Cloud Vertex AI, with availability on NVIDIA NIM andStarting Price: Free -
10
Yi-Large
01.AI
Yi-Large is a proprietary large language model developed by 01.AI, offering a 32k context length with both input and output costs at $2 per million tokens. It stands out with its advanced capabilities in natural language processing, common-sense reasoning, and multilingual support, performing on par with leading models like GPT-4 and Claude3 in various benchmarks. Yi-Large is designed for tasks requiring complex inference, prediction, and language understanding, making it suitable for applications like knowledge search, data classification, and creating human-like chatbots. Its architecture is based on a decoder-only transformer with enhancements such as pre-normalization and Group Query Attention, and it has been trained on a vast, high-quality multilingual dataset. This model's versatility and cost-efficiency make it a strong contender in the AI market, particularly for enterprises aiming to deploy AI solutions globally.Starting Price: $0.19 per 1M input token -
11
OLMo 2
Ai2
OLMo 2 is a family of fully open language models developed by the Allen Institute for AI (AI2), designed to provide researchers and developers with transparent access to training data, open-source code, reproducible training recipes, and comprehensive evaluations. These models are trained on up to 5 trillion tokens and are competitive with leading open-weight models like Llama 3.1 on English academic benchmarks. OLMo 2 emphasizes training stability, implementing techniques to prevent loss spikes during long training runs, and utilizes staged training interventions during late pretraining to address capability deficiencies. The models incorporate state-of-the-art post-training methodologies from AI2's Tülu 3, resulting in the creation of OLMo 2-Instruct models. An actionable evaluation framework, the Open Language Modeling Evaluation System (OLMES), was established to guide improvements through development stages, consisting of 20 evaluation benchmarks assessing core capabilities. -
12
PanGu-Σ
Huawei
Significant advancements in the field of natural language processing, understanding, and generation have been achieved through the expansion of large language models. This study introduces a system which utilizes Ascend 910 AI processors and the MindSpore framework to train a language model with over a trillion parameters, specifically 1.085T, named PanGu-{\Sigma}. This model, which builds upon the foundation laid by PanGu-{\alpha}, takes the traditionally dense Transformer model and transforms it into a sparse one using a concept known as Random Routed Experts (RRE). The model was efficiently trained on a dataset of 329 billion tokens using a technique called Expert Computation and Storage Separation (ECSS), leading to a 6.3-fold increase in training throughput via heterogeneous computing. Experimentation indicates that PanGu-{\Sigma} sets a new standard in zero-shot learning for various downstream Chinese NLP tasks. -
13
ERNIE 3.0 Titan
Baidu
Pre-trained language models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. GPT-3 has shown that scaling up pre-trained language models can further exploit their enormous potential. A unified framework named ERNIE 3.0 was recently proposed for pre-training large-scale knowledge enhanced models and trained a model with 10 billion parameters. ERNIE 3.0 outperformed the state-of-the-art models on various NLP tasks. In order to explore the performance of scaling up ERNIE 3.0, we train a hundred-billion-parameter model called ERNIE 3.0 Titan with up to 260 billion parameters on the PaddlePaddle platform. Furthermore, We design a self-supervised adversarial loss and a controllable language modeling loss to make ERNIE 3.0 Titan generate credible and controllable texts. -
14
Baichuan-13B
Baichuan Intelligent Technology
Baichuan-13B is an open source and commercially available large-scale language model containing 13 billion parameters developed by Baichuan Intelligent following Baichuan -7B . It has achieved the best results of the same size on authoritative Chinese and English benchmarks. This release contains two versions of pre-training ( Baichuan-13B-Base ) and alignment ( Baichuan-13B-Chat ). Larger size, more data : Baichuan-13B further expands the number of parameters to 13 billion on the basis of Baichuan -7B , and trains 1.4 trillion tokens on high-quality corpus, which is 40% more than LLaMA-13B. It is currently open source The model with the largest amount of training data in the 13B size. Support Chinese and English bilingual, use ALiBi position code, context window length is 4096.Starting Price: Free -
15
Qwen-7B
Alibaba
Qwen-7B is the 7B-parameter version of the large language model series, Qwen (abbr. Tongyi Qianwen), proposed by Alibaba Cloud. Qwen-7B is a Transformer-based large language model, which is pretrained on a large volume of data, including web texts, books, codes, etc. Additionally, based on the pretrained Qwen-7B, we release Qwen-7B-Chat, a large-model-based AI assistant, which is trained with alignment techniques. The features of the Qwen-7B series include: Trained with high-quality pretraining data. We have pretrained Qwen-7B on a self-constructed large-scale high-quality dataset of over 2.2 trillion tokens. The dataset includes plain texts and codes, and it covers a wide range of domains, including general domain data and professional domain data. Strong performance. In comparison with the models of the similar model size, we outperform the competitors on a series of benchmark datasets, which evaluates natural language understanding, mathematics, coding, etc. And more.Starting Price: Free -
16
Alpa
Alpa
Alpa aims to automate large-scale distributed training and serving with just a few lines of code. Alpa was initially developed by folks in the Sky Lab, UC Berkeley. Some advanced techniques used in Alpa have been written in a paper published in OSDI'2022. Alpa community is growing with new contributors from Google. A language model is a probability distribution over sequences of words. It predicts the next word based on all the previous words. It is useful for a variety of AI applications, such the auto-completion in your email or chatbot service. For more information, check out the language model wikipedia page. GPT-3 is very large language model, with 175 billion parameters, that uses deep learning to produce human-like text. Many researchers and news articles described GPT-3 as "one of the most interesting and important AI systems ever produced". GPT-3 is gradually being used as a backbone in the latest NLP research and applications.Starting Price: Free -
17
Gemini Flash
Google
Gemini Flash is an advanced large language model (LLM) from Google, specifically designed for high-speed, low-latency language processing tasks. Part of Google DeepMind’s Gemini series, Gemini Flash is tailored to provide real-time responses and handle large-scale applications, making it ideal for interactive AI-driven experiences such as customer support, virtual assistants, and live chat solutions. Despite its speed, Gemini Flash doesn’t compromise on quality; it’s built on sophisticated neural architectures that ensure responses remain contextually relevant, coherent, and precise. Google has incorporated rigorous ethical frameworks and responsible AI practices into Gemini Flash, equipping it with guardrails to manage and mitigate biased outputs, ensuring it aligns with Google’s standards for safe and inclusive AI. With Gemini Flash, Google empowers businesses and developers to deploy responsive, intelligent language tools that can meet the demands of fast-paced environments. -
18
T5
Google
With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input. Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task, including machine translation, document summarization, question answering, and classification tasks (e.g., sentiment analysis). We can even apply T5 to regression tasks by training it to predict the string representation of a number instead of the number itself. -
19
DeepSeek-V2
DeepSeek
DeepSeek-V2 is a state-of-the-art Mixture-of-Experts (MoE) language model introduced by DeepSeek-AI, characterized by its economical training and efficient inference capabilities. With a total of 236 billion parameters, of which only 21 billion are active per token, it supports a context length of up to 128K tokens. DeepSeek-V2 employs innovative architectures like Multi-head Latent Attention (MLA) for efficient inference by compressing the Key-Value (KV) cache and DeepSeekMoE for cost-effective training through sparse computation. This model significantly outperforms its predecessor, DeepSeek 67B, by saving 42.5% in training costs, reducing the KV cache by 93.3%, and enhancing generation throughput by 5.76 times. Pretrained on an 8.1 trillion token corpus, DeepSeek-V2 excels in language understanding, coding, and reasoning tasks, making it a top-tier performer among open-source models.Starting Price: Free -
20
Grok 3
xAI
Grok-3, developed by xAI, represents a significant advancement in the field of artificial intelligence, aiming to set new benchmarks in AI capabilities. It is designed to be a multimodal AI, capable of processing and understanding data from various sources including text, images, and audio, which allows for a more integrated and comprehensive interaction with users. Grok-3 is built on an unprecedented scale, with training involving ten times more computational resources than its predecessor, leveraging 100,000 Nvidia H100 GPUs on the Colossus supercomputer. This extensive computational power is expected to enhance Grok-3's performance in areas like reasoning, coding, and real-time analysis of current events through direct access to X posts. The model is anticipated to outperform not only its earlier versions but also compete with other leading AI models in the generative AI landscape.Starting Price: Free -
21
Codestral Mamba
Mistral AI
As a tribute to Cleopatra, whose glorious destiny ended in tragic snake circumstances, we are proud to release Codestral Mamba, a Mamba2 language model specialized in code generation, available under an Apache 2.0 license. Codestral Mamba is another step in our effort to study and provide new architectures. It is available for free use, modification, and distribution, and we hope it will open new perspectives in architecture research. Mamba models offer the advantage of linear time inference and the theoretical ability to model sequences of infinite length. It allows users to engage with the model extensively with quick responses, irrespective of the input length. This efficiency is especially relevant for code productivity use cases, this is why we trained this model with advanced code and reasoning capabilities, enabling it to perform on par with SOTA transformer-based models.Starting Price: Free -
22
Teuken 7B
OpenGPT-X
Teuken-7B is a multilingual, open source language model developed under the OpenGPT-X initiative, specifically designed to cater to Europe's diverse linguistic landscape. It has been trained on a dataset comprising over 50% non-English texts, encompassing all 24 official languages of the European Union, ensuring robust performance across these languages. A key innovation in Teuken-7B is its custom multilingual tokenizer, optimized for European languages, which enhances training efficiency and reduces inference costs compared to standard monolingual tokenizers. The model is available in two versions, Teuken-7B-Base, the foundational pre-trained model, and Teuken-7B-Instruct, which has undergone instruction tuning for improved performance in following user prompts. Both versions are accessible on Hugging Face, promoting transparency and collaboration within the AI community. The development of Teuken-7B underscores a commitment to creating AI models that reflect Europe's diversity.Starting Price: Free -
23
Gemma 2
Google
A family of state-of-the-art, light-open models created from the same research and technology that were used to create Gemini models. These models incorporate comprehensive security measures and help ensure responsible and reliable AI solutions through selected data sets and rigorous adjustments. Gemma models achieve exceptional comparative results in their 2B, 7B, 9B, and 27B sizes, even outperforming some larger open models. With Keras 3.0, enjoy seamless compatibility with JAX, TensorFlow, and PyTorch, allowing you to effortlessly choose and change frameworks based on task. Redesigned to deliver outstanding performance and unmatched efficiency, Gemma 2 is optimized for incredibly fast inference on various hardware. The Gemma family of models offers different models that are optimized for specific use cases and adapt to your needs. Gemma models are large text-to-text lightweight language models with a decoder, trained in a huge set of text data, code, and mathematical content. -
24
NVIDIA Nemotron
NVIDIA
NVIDIA Nemotron is a family of open-source models developed by NVIDIA, designed to generate synthetic data for training large language models (LLMs) for commercial applications. The Nemotron-4 340B model, in particular, is a significant release by NVIDIA, offering developers a powerful tool to generate high-quality data and filter it based on various attributes using a reward model. -
25
Qwen2.5-Max
Alibaba
Qwen2.5-Max is a large-scale Mixture-of-Experts (MoE) model developed by the Qwen team, pretrained on over 20 trillion tokens and further refined through Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF). In evaluations, it outperforms models like DeepSeek V3 in benchmarks such as Arena-Hard, LiveBench, LiveCodeBench, and GPQA-Diamond, while also demonstrating competitive results in other assessments, including MMLU-Pro. Qwen2.5-Max is accessible via API through Alibaba Cloud and can be explored interactively on Qwen Chat.Starting Price: Free -
26
Chinchilla
Google DeepMind
Chinchilla is a large language model. Chinchilla uses the same compute budget as Gopher but with 70B parameters and 4× more more data. Chinchilla uniformly and significantly outperforms Gopher (280B), GPT-3 (175B), Jurassic-1 (178B), and Megatron-Turing NLG (530B) on a large range of downstream evaluation tasks. This also means that Chinchilla uses substantially less compute for fine-tuning and inference, greatly facilitating downstream usage. As a highlight, Chinchilla reaches a state-of-the-art average accuracy of 67.5% on the MMLU benchmark, greater than a 7% improvement over Gopher. -
27
Llama 2
Meta
The next generation of our open source large language model. This release includes model weights and starting code for pretrained and fine-tuned Llama language models — ranging from 7B to 70B parameters. Llama 2 pretrained models are trained on 2 trillion tokens, and have double the context length than Llama 1. Its fine-tuned models have been trained on over 1 million human annotations. Llama 2 outperforms other open source language models on many external benchmarks, including reasoning, coding, proficiency, and knowledge tests. Llama 2 was pretrained on publicly available online data sources. The fine-tuned model, Llama-2-chat, leverages publicly available instruction datasets and over 1 million human annotations. We have a broad range of supporters around the world who believe in our open approach to today’s AI — companies that have given early feedback and are excited to build with Llama 2.Starting Price: Free -
28
VideoPoet
Google
VideoPoet is a simple modeling method that can convert any autoregressive language model or large language model (LLM) into a high-quality video generator. It contains a few simple components. An autoregressive language model learns across video, image, audio, and text modalities to autoregressively predict the next video or audio token in the sequence. A mixture of multimodal generative learning objectives are introduced into the LLM training framework, including text-to-video, text-to-image, image-to-video, video frame continuation, video inpainting and outpainting, video stylization, and video-to-audio. Furthermore, such tasks can be composed together for additional zero-shot capabilities. This simple recipe shows that language models can synthesize and edit videos with a high degree of temporal consistency. -
29
MiniMax-M1
MiniMax
MiniMax‑M1 is a large‑scale hybrid‑attention reasoning model released by MiniMax AI under the Apache 2.0 license. It supports an unprecedented 1 million‑token context window and up to 80,000-token outputs, enabling extended reasoning across long documents. Trained using large‑scale reinforcement learning with a novel CISPO algorithm, MiniMax‑M1 completed full training on 512 H800 GPUs in about three weeks. It achieves state‑of‑the‑art performance on benchmarks in mathematics, coding, software engineering, tool usage, and long‑context understanding, matching or outperforming leading models. Two model variants are available (40K and 80K thinking budgets), with weights and deployment scripts provided via GitHub and Hugging Face. -
30
GPT-4
OpenAI
GPT-4 (Generative Pre-trained Transformer 4) is a large-scale unsupervised language model, yet to be released by OpenAI. GPT-4 is the successor to GPT-3 and part of the GPT-n series of natural language processing models, and was trained on a dataset of 45TB of text to produce human-like text generation and understanding capabilities. Unlike most other NLP models, GPT-4 does not require additional training data for specific tasks. Instead, it can generate text or answer questions using only its own internally generated context as input. GPT-4 has been shown to be able to perform a wide variety of tasks without any task specific training data such as translation, summarization, question answering, sentiment analysis and more.Starting Price: $0.0200 per 1000 tokens -
31
GPT4All
Nomic AI
GPT4All is an ecosystem to train and deploy powerful and customized large language models that run locally on consumer-grade CPUs. The goal is simple - be the best instruction-tuned assistant-style language model that any person or enterprise can freely use, distribute and build on. A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. Nomic AI supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models. Data is one the most important ingredients to successfully building a powerful, general-purpose large language model. The GPT4All community has built the GPT4All open source data lake as a staging ground for contributing instruction and assistant tuning data for future GPT4All model trains.Starting Price: Free -
32
Ferret
Apple
An End-to-End MLLM that Accept Any-Form Referring and Ground Anything in Response. Ferret Model - Hybrid Region Representation + Spatial-aware Visual Sampler enable fine-grained and open-vocabulary referring and grounding in MLLM. GRIT Dataset (~1.1M) - A Large-scale, Hierarchical, Robust ground-and-refer instruction tuning dataset. Ferret-Bench - A multimodal evaluation benchmark that jointly requires Referring/Grounding, Semantics, Knowledge, and Reasoning.Starting Price: Free -
33
mT5
Google
Multilingual T5 (mT5) is a massively multilingual pretrained text-to-text transformer model, trained following a similar recipe as T5. This repo can be used to reproduce the experiments in the mT5 paper. mT5 is pretrained on the mC4 corpus, covering 101 languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Scottish Gaelic, Serbian, Shona, Sindhi, and more.Starting Price: Free -
34
PanGu-α
Huawei
PanGu-α is developed under the MindSpore and trained on a cluster of 2048 Ascend 910 AI processors. The training parallelism strategy is implemented based on MindSpore Auto-parallel, which composes five parallelism dimensions to scale the training task to 2048 processors efficiently, including data parallelism, op-level model parallelism, pipeline model parallelism, optimizer model parallelism and rematerialization. To enhance the generalization ability of PanGu-α, we collect 1.1TB high-quality Chinese data from a wide range of domains to pretrain the model. We empirically test the generation ability of PanGu-α in various scenarios including text summarization, question answering, dialogue generation, etc. Moreover, we investigate the effect of model scales on the few-shot performances across a broad range of Chinese NLP tasks. The experimental results demonstrate the superior capabilities of PanGu-α in performing various tasks under few-shot or zero-shot settings. -
35
LLaVA
LLaVA
LLaVA (Large Language-and-Vision Assistant) is an innovative multimodal model that integrates a vision encoder with the Vicuna language model to facilitate comprehensive visual and language understanding. Through end-to-end training, LLaVA exhibits impressive chat capabilities, emulating the multimodal functionalities of models like GPT-4. Notably, LLaVA-1.5 has achieved state-of-the-art performance across 11 benchmarks, utilizing publicly available data and completing training in approximately one day on a single 8-A100 node, surpassing methods that rely on billion-scale datasets. The development of LLaVA involved the creation of a multimodal instruction-following dataset, generated using language-only GPT-4. This dataset comprises 158,000 unique language-image instruction-following samples, including conversations, detailed descriptions, and complex reasoning tasks. This data has been instrumental in training LLaVA to perform a wide array of visual and language tasks effectively.Starting Price: Free -
36
Llama 3.3
Meta
Llama 3.3 is the latest iteration in the Llama series of language models, developed to push the boundaries of AI-powered understanding and communication. With enhanced contextual reasoning, improved language generation, and advanced fine-tuning capabilities, Llama 3.3 is designed to deliver highly accurate, human-like responses across diverse applications. This version features a larger training dataset, refined algorithms for nuanced comprehension, and reduced biases compared to its predecessors. Llama 3.3 excels in tasks such as natural language understanding, creative writing, technical explanation, and multilingual communication, making it an indispensable tool for businesses, developers, and researchers. Its modular architecture allows for customizable deployment in specialized domains, ensuring versatility and performance at scale.Starting Price: Free -
37
PaLM 2
Google
PaLM 2 is our next generation large language model that builds on Google’s legacy of breakthrough research in machine learning and responsible AI. It excels at advanced reasoning tasks, including code and math, classification and question answering, translation and multilingual proficiency, and natural language generation better than our previous state-of-the-art LLMs, including PaLM. It can accomplish these tasks because of the way it was built – bringing together compute-optimal scaling, an improved dataset mixture, and model architecture improvements. PaLM 2 is grounded in Google’s approach to building and deploying AI responsibly. It was evaluated rigorously for its potential harms and biases, capabilities and downstream uses in research and in-product applications. It’s being used in other state-of-the-art models, like Med-PaLM 2 and Sec-PaLM, and is powering generative AI features and tools at Google, like Bard and the PaLM API. -
38
Mistral Small
Mistral AI
On September 17, 2024, Mistral AI announced several key updates to enhance the accessibility and performance of their AI offerings. They introduced a free tier on "La Plateforme," their serverless platform for tuning and deploying Mistral models as API endpoints, enabling developers to experiment and prototype at no cost. Additionally, Mistral AI reduced prices across their entire model lineup, with significant cuts such as a 50% reduction for Mistral Nemo and an 80% decrease for Mistral Small and Codestral, making advanced AI more cost-effective for users. The company also unveiled Mistral Small v24.09, a 22-billion-parameter model offering a balance between performance and efficiency, suitable for tasks like translation, summarization, and sentiment analysis. Furthermore, they made Pixtral 12B, a vision-capable model with image understanding capabilities, freely available on "Le Chat," allowing users to analyze and caption images without compromising text-based performance.Starting Price: Free -
39
Llama 3.1
Meta
The open source AI model you can fine-tune, distill and deploy anywhere. Our latest instruction-tuned model is available in 8B, 70B and 405B versions. Using our open ecosystem, build faster with a selection of differentiated product offerings to support your use cases. Choose from real-time inference or batch inference services. Download model weights to further optimize cost per token. Adapt for your application, improve with synthetic data and deploy on-prem or in the cloud. Use Llama system components and extend the model using zero shot tool use and RAG to build agentic behaviors. Leverage 405B high quality data to improve specialized models for specific use cases.Starting Price: Free -
40
RoBERTa
Meta
RoBERTa builds on BERT’s language masking strategy, wherein the system learns to predict intentionally hidden sections of text within otherwise unannotated language examples. RoBERTa, which was implemented in PyTorch, modifies key hyperparameters in BERT, including removing BERT’s next-sentence pretraining objective, and training with much larger mini-batches and learning rates. This allows RoBERTa to improve on the masked language modeling objective compared with BERT and leads to better downstream task performance. We also explore training RoBERTa on an order of magnitude more data than BERT, for a longer amount of time. We used existing unannotated NLP datasets as well as CC-News, a novel set drawn from public news articles.Starting Price: Free -
41
Mercury Coder
Inception Labs
Mercury, the latest innovation from Inception Labs, is the first commercial-scale diffusion large language model (dLLM), offering a 10x speed increase and significantly lower costs compared to traditional autoregressive models. Built for high-performance reasoning, coding, and structured text generation, Mercury processes over 1000 tokens per second on NVIDIA H100 GPUs, making it one of the fastest LLMs available. Unlike conventional models that generate text one token at a time, Mercury refines responses using a coarse-to-fine diffusion approach, improving accuracy and reducing hallucinations. With Mercury Coder, a specialized coding model, developers can experience cutting-edge AI-driven code generation with superior speed and efficiency.Starting Price: Free -
42
Mistral Large 2
Mistral AI
Mistral AI has launched the Mistral Large 2, an advanced AI model designed to excel in code generation, multilingual capabilities, and complex reasoning tasks. The model features a 128k context window, supporting dozens of languages including English, French, Spanish, and Arabic, as well as over 80 programming languages. Mistral Large 2 is tailored for high-throughput single-node inference, making it ideal for large-context applications. Its improved performance on benchmarks like MMLU and its enhanced code generation and reasoning abilities ensure accuracy and efficiency. The model also incorporates better function calling and retrieval, supporting complex business applications.Starting Price: Free -
43
Yi-Lightning
Yi-Lightning
Yi-Lightning, developed by 01.AI under the leadership of Kai-Fu Lee, represents the latest advancement in large language models with a focus on high performance and cost-efficiency. It boasts a maximum context length of 16K tokens and is priced at $0.14 per million tokens for both input and output, making it remarkably competitive. Yi-Lightning leverages an enhanced Mixture-of-Experts (MoE) architecture, incorporating fine-grained expert segmentation and advanced routing strategies, which contribute to its efficiency in training and inference. This model has excelled in various domains, achieving top rankings in categories like Chinese, math, coding, and hard prompts on the chatbot arena, where it secured the 6th position overall and 9th in style control. Its development included comprehensive pre-training, supervised fine-tuning, and reinforcement learning from human feedback, ensuring both performance and safety, with optimizations in memory usage and inference speed. -
44
DBRX
Databricks
Today, we are excited to introduce DBRX, an open, general-purpose LLM created by Databricks. Across a range of standard benchmarks, DBRX sets a new state-of-the-art for established open LLMs. Moreover, it provides the open community and enterprises building their own LLMs with capabilities that were previously limited to closed model APIs; according to our measurements, it surpasses GPT-3.5, and it is competitive with Gemini 1.0 Pro. It is an especially capable code model, surpassing specialized models like CodeLLaMA-70B in programming, in addition to its strength as a general-purpose LLM. This state-of-the-art quality comes with marked improvements in training and inference performance. DBRX advances the state-of-the-art in efficiency among open models thanks to its fine-grained mixture-of-experts (MoE) architecture. Inference is up to 2x faster than LLaMA2-70B, and DBRX is about 40% of the size of Grok-1 in terms of both total and active parameter counts. -
45
LongLLaMA
LongLLaMA
This repository contains the research preview of LongLLaMA, a large language model capable of handling long contexts of 256k tokens or even more. LongLLaMA is built upon the foundation of OpenLLaMA and fine-tuned using the Focused Transformer (FoT) method. LongLLaMA code is built upon the foundation of Code Llama. We release a smaller 3B base variant (not instruction tuned) of the LongLLaMA model on a permissive license (Apache 2.0) and inference code supporting longer contexts on hugging face. Our model weights can serve as the drop-in replacement of LLaMA in existing implementations (for short context up to 2048 tokens). Additionally, we provide evaluation results and comparisons against the original OpenLLaMA models.Starting Price: Free -
46
Falcon-7B
Technology Innovation Institute (TII)
Falcon-7B is a 7B parameters causal decoder-only model built by TII and trained on 1,500B tokens of RefinedWeb enhanced with curated corpora. It is made available under the Apache 2.0 license. Why use Falcon-7B? It outperforms comparable open-source models (e.g., MPT-7B, StableLM, RedPajama etc.), thanks to being trained on 1,500B tokens of RefinedWeb enhanced with curated corpora. See the OpenLLM Leaderboard. It features an architecture optimized for inference, with FlashAttention and multiquery. It is made available under a permissive Apache 2.0 license allowing for commercial use, without any royalties or restrictions.Starting Price: Free -
47
Qwen2.5-1M
Alibaba
Qwen2.5-1M is an open-source language model developed by the Qwen team, designed to handle context lengths of up to one million tokens. This release includes two model variants, Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, marking the first time Qwen models have been upgraded to support such extensive context lengths. To facilitate efficient deployment, the team has also open-sourced an inference framework based on vLLM, integrated with sparse attention methods, enabling processing of 1M-token inputs with a 3x to 7x speed improvement. Comprehensive technical details, including design insights and ablation experiments, are available in the accompanying technical report.Starting Price: Free -
48
Falcon-40B
Technology Innovation Institute (TII)
Falcon-40B is a 40B parameters causal decoder-only model built by TII and trained on 1,000B tokens of RefinedWeb enhanced with curated corpora. It is made available under the Apache 2.0 license. Why use Falcon-40B? It is the best open-source model currently available. Falcon-40B outperforms LLaMA, StableLM, RedPajama, MPT, etc. See the OpenLLM Leaderboard. It features an architecture optimized for inference, with FlashAttention and multiquery. It is made available under a permissive Apache 2.0 license allowing for commercial use, without any royalties or restrictions. ⚠️ This is a raw, pretrained model, which should be further finetuned for most usecases. If you are looking for a version better suited to taking generic instructions in a chat format, we recommend taking a look at Falcon-40B-Instruct.Starting Price: Free -
49
BitNet
Microsoft
The BitNet b1.58 2B4T is a cutting-edge 1-bit Large Language Model (LLM) developed by Microsoft, designed to enhance computational efficiency while maintaining high performance. This model, built with approximately 2 billion parameters and trained on 4 trillion tokens, uses innovative quantization techniques to optimize memory usage, energy consumption, and latency. The platform supports multiple modalities and is particularly valuable for applications in AI-powered text generation, offering substantial efficiency gains compared to full-precision models.Starting Price: Free -
50
StarCoder
BigCode
StarCoder and StarCoderBase are Large Language Models for Code (Code LLMs) trained on permissively licensed data from GitHub, including from 80+ programming languages, Git commits, GitHub issues, and Jupyter notebooks. Similar to LLaMA, we trained a ~15B parameter model for 1 trillion tokens. We fine-tuned StarCoderBase model for 35B Python tokens, resulting in a new model that we call StarCoder. We found that StarCoderBase outperforms existing open Code LLMs on popular programming benchmarks and matches or surpasses closed models such as code-cushman-001 from OpenAI (the original Codex model that powered early versions of GitHub Copilot). With a context length of over 8,000 tokens, the StarCoder models can process more input than any other open LLM, enabling a wide range of interesting applications. For example, by prompting the StarCoder models with a series of dialogues, we enabled them to act as a technical assistant.Starting Price: Free