Models

This page provides information about the different models used by the Prediction Guard API.

Hermes-3-Llama-3.1-8B

This is a general use model that excels at reasoning and multi-turn conversations, with an improved focus on longer context lengths. This allows for more accuracy and recall in areas that require a longer context window, along with being an improved version of the previous Hermes and Llama line of models.

Type: Chat
Use Case: Instruction Following or Chat-Like Applications
Prompt Format: ChatML\

https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.

The ethos of the Hermes series of models is focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.

The Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.

Hermes-2-Pro-Llama-3-8B

A general use model that maintains excellent general task and conversation capabilities while excelling at JSON Structured Outputs and improving on several other metrics.

Type: Chat
Use Case: Instruction Following or Chat-Like Applications
Prompt Format: ChatML\

https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.

This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.

Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse.

Nous-Hermes-Llama2-13b

A general use model that combines advanced analytics capabilities with a vast 13 billion parameter count, enabling it to perform in-depth data analysis and support complex decision-making processes. This model is designed to process large volumes of data, uncover hidden patterns, and provide actionable insights.

Type: Text Generation
Use Case: Generating Output in Response to Arbitrary Instructions
Prompt Format: Alpaca\

https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b

Nous-Hermes-Llama2-13b is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium and Emozilla leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors.

This Hermes model uses the exact same dataset as Hermes on Llama-1. This is to ensure consistency between the old Hermes and new, for anyone who wanted to keep Hermes as similar to the old one, just more capable.

This model stands out for its long responses, lower hallucination rate, and absence of OpenAI censorship mechanisms. The fine-tuning process was performed with a 4096 sequence length on an 8x a100 80GB DGX machine.

Hermes-2-Pro-Mistral-7B

A general use model that offers advanced natural language understanding and generation capabilities, empowering applications with high-performance text-processing functionalities across diverse domains and languages. The model excels in delivering accurate and contextually relevant responses, making it ideal for a wide range of applications, including chatbots, language translation, content creation, and more.

Type: Chat
Use Case: Instruction Following or Chat-Like Applications
Prompt Format: ChatML\

https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B

Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.

neural-chat-7b-v3-3

A revolutionary AI model for performing digital conversations.

Type: Chat
Use Case: Instruction Following or Chat-Like Applications
Prompt Format: Neural Chat\

https://huggingface.co/Intel/neural-chat-7b-v3-3

This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the Intel/neural-chat-7b-v3-1 on the meta-math/MetaMathQA dataset. The model was aligned using the Direct Performance Optimization (DPO) method with Intel/orca_dpo_pairs. The Intel/neural-chat-7b-v3-1 was originally fine-tuned from mistralai/Mistral-7B-v-0.1. For more information, refer to the blog

The Practice of Supervised Fine-tuning and Direct Preference Optimization on Intel Gaudi2

deepseek-coder-6.7b-instruct

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

Type: Code Generation
Use Case: Generating Computer Code or Answering Tech Questions
Prompt Format: Deepseek\

https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. We provide various sizes of the code model, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fill-in-the-blank task, to support project-level code completion and infilling. For coding capabilities, Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.

multilingual-e5-large-instruct

Multilingual-e5 is a multilingual model for creating text embeddings in multiple languages.

Type: Embedding Generation
Use Case: Used for Generating Text Embeddings\

https://huggingface.co/intfloat/multilingual-e5-large-instruct

multilingual-e5-large-instruct is a robust, multilingual embedding model with 560 million parameters and a dimensionality of 1024, capable of processing inputs with up to 512 tokens. This model builds on the xlm-roberta-large architecture and is designed to excel in multilingual text embedding tasks across 100 languages. Trained through a two-stage process, it first undergoes contrastive pre-training on one billion weakly supervised text pairs, followed by fine-tuning on diverse multilingual datasets from the E5-mistral paper.

With state-of-the-art performance in text retrieval and semantic similarity, this model demonstrates impressive results on the BEIR and MTEB benchmarks. Users should note that task instructions are crucial for optimal performance, as the model leverages these to customize embeddings for various scenarios. Although the model generally supports 100 languages, performance may vary for low-resource languages.

With a training approach that mirrors the English E5 model recipe, it achieves comparable quality to leading English-only models while offering a multilingual edge.

bridgetower-large-itm-mlm-itc

BridgeTower is a multimodal model for creating joint embeddings between images and text.

Type: Embedding Generation
Use Case: Used for Generating Text and Image Embedding\

https://huggingface.co/BridgeTower/bridgetower-large-itm-mlm-itc

BridgeTower introduces multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the cross-modal encoder. This enables effective bottom-up cross-modal alignment and fusion between visual and textual representations of different semantic levels of pre-trained uni-modal encoders in the cross-modal encoder. Pre-trained with only 4M images, BridgeTower achieves state-of-the-art performance on various downstream vision-language tasks. In particular, on the VQAv2 test-std set, BridgeTower achieves an accuracy of 78.73%, outperforming the previous state-of-the-art model METER by 1.09% with the same pre-training data and almost negligible additional parameters and computational costs. Notably, when further scaling the model, BridgeTower achieves an accuracy of 81.15%, surpassing models that are pre-trained on orders-of-magnitude larger datasets.

llava-1.5-7b-hf

LLaVa is a multimodal model that supports vision and language models combined.

This Model is required to be used with the /chat/completions vision endpoint. Most of the SDKs will not ask you to provide model because it’s using this one.

Type: Vision Text Generation
Use Case: Used for Generating Text from Text and Image Inputs\

https://huggingface.co/llava-hf/llava-1.5-7b-hf

LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

Hermes-3-Llama-3.1-70B (beta)

Note: This model should be considered beta/experimental as of now. Please let us know if you have any issues via Discord.

Type: Chat
Use Case: Instruction Following or Chat-Like Applications
Prompt Format: ChatML\

https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B

The ethos of the Hermes series of models is focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.