Skip to content

Nous Research · Chat

NousResearch: Hermes 2 Pro - Llama-3 8B

Nous Research 🇺🇸ChatLlama familyOpen weights. One of its sources says the weights are publicly available.
llminfo IQ
94.7
Market median price
$0.14 blended / 1M
Max context
8K
Listings
4

Evidence and sources

🤗 nousresearch/hermes-2-pro-llama-3-8bllminfo IQ 94.7, ranked among chat models. From 6 benchmarks. A fair amount of data behind it.How llminfo IQ is computedReleased 30 Apr 2024Maker HQ: US (source)
Sources: Novita AI data, FlowDot data, Models.dev data, Hugging FacePrimary data from Novita AI from FlowDot: name from Models.dev: weights availability from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 6 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Text

Listings

 Flowdotnousresearch/hermes-2-pro-llama-3-8bSource: FlowDot data8K$0.14$0.14
 Hugging FaceInference by Novita AINousResearch/Hermes-2-Pro-Llama-3-8BSource: GenAI Prices data8K$0.14$0.14
 OpenRouternousresearch/hermes-2-pro-llama-3-8bSource: GenAI Prices dataNot published by the provider$0.025$0.04
 Novita AInousresearch/hermes-2-pro-llama-3-8bSources: GenAI Prices data, LiteLLM data, Models.dev data, Novita AI data8K$0.14$0.14

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Reasoning

Instruction following

Knowledge

Math

Science

Around the web

  • Open-source AI Models for Any Application | Llama 3
    docs Learn Cookbooks Videos Blog Case studies Community Github Meta-Models Llama Hugging Face Llama Safety …docs Learn Cookbooks Videos Blog Case studies Community Github Meta-Models Llama Hugging Face Llama Safety Llama Protections Overview Llama Defenders Program Developer use guide Build with Muse Spark…

    developer.meta.com

  • The Llama 3 Herd of Models | Research - AI at Meta
    Meta Products AI Research Resources About AI Developers Try Meta AI HUMAN & MACHINE INTELLIGENCE …Meta Products AI Research Resources About AI Developers Try Meta AI HUMAN & MACHINE INTELLIGENCE CONVERSATIONAL AI The Llama 3 Herd of Models July 23, 2024 Abstract Modern artificial intelligence (AI…

    ai.meta.com

  • Open-source AI Models for Any Application | Llama 3
    research community Network Hugging Face GitHub Safety Llama Protections Overview Llama Defenders Program Developer use …research community Network Hugging Face GitHub Safety Llama Protections Overview Llama Defenders Program Developer use guide Llama API Models Models families Llama 3 Stay updated Download models Llam…

    llama.com

  • IBM Offers Meta’s Llama 3 Open Models on Watsonx, Expands Portfolio of Next Generation Enterprise-Ready Models
    support a broad range of use cases including summarization, classification, information extraction, and content grounded …support a broad range of use cases including summarization, classification, information extraction, and content grounded question and answering. The 8B model is designed for faster training and edge …

    newsroom.ibm.com

  • Llama 3 · Ollama Blog
    Llama 3 April 18, 2024 3 Ollamas Llama 3 is now available to run using …Llama 3 April 18, 2024 3 Ollamas Llama 3 is now available to run using Ollama. To get started, Download Ollama and run Llama 3: ollama run llama3 The most capable model Llama 3 represents a large imp…

    ollama.com

  • llama-models/models/llama3/MODEL_CARD.md at main · meta-llama/llama-models · GitHub
    is used for all models to improve inference efficiency. The tuned versions use supervised fine-tuning …is used for all models to improve inference efficiency. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for h…

    github.com

  • Meta says Llama 3 beats most other models, including Gemini | The Verge
    In the MMLU benchmark, which typically measures general knowledge, Llama 3 8B performed significantly better …In the MMLU benchmark, which typically measures general knowledge, Llama 3 8B performed significantly better than both Gemma 7B and Mistral 7B, while Llama 3 70B slightly edged Gemini Pro 1.5 . (It i…

    theverge.com

  • Meta Releases Llama 3 Open-Source LLM - InfoQ
    The research team also found that training the model with more than the Chinchilla-optimal amount …The research team also found that training the model with more than the Chinchilla-optimal amount of compute brought continued performance gains. In the first week after the Llama 3 release, Meta cla…

    infoq.com

  • GitHub - meta-llama/llama3: The official Meta Llama 3 GitHub site · GitHub
    their ideas responsibly. This release includes model weights and starting code for pre-trained and instruction-tuned …their ideas responsibly. This release includes model weights and starting code for pre-trained and instruction-tuned Llama 3 language models — including sizes of 8B to 70B parameters. This repository…

    github.com

  • Llama 3 Establishes Meta as the Leader in “Open” AI - IEEE Spectrum
    that the [hardware] vendors are maturing, and that the industry is maturing.” Open-source developers have …that the [hardware] vendors are maturing, and that the industry is maturing.” Open-source developers have embraced Llama 3 with similar speed. Llama 3 8B tops the list of trending models on the AI de…

    spectrum.ieee.org

Also known as: novita/nousresearch/hermes-2-pro-llama-3-8b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works