Skip to content

Mlabonne · Chat

Neural Daredevil 8B abliterated

MlabonneChatOpen weights. One of its sources says the weights are publicly available.
From NanoGPT's listing:
The best performing 8B abliterated model according to most benchmarks.
llminfo IQ
95.0
Market median price
$0.44 blended / 1M
Max context
8K
Listings
2

Evidence and sources

🤗 mlabonne/NeuralDaredevil-8B-abliteratedllminfo IQ 95.0, ranked among chat models. From 6 benchmarks. A fair amount of data behind it.How llminfo IQ is computedReleased 13 Jun 2024
All rankings: #400 on NanoGPT recentlySources: Models.dev data, NanoGPT, llminfo researchPrimary data from Models.dev from NanoGPT: description from llminfo research: 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.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

Prompt caching

Listings

 NanoGPTmlabonne/NeuralDaredevil-8B-abliteratedSources: Models.dev data, NanoGPT8K$0.44cache read $0.22$0.44
 NanoGPTInference by KitaniRegions: GLBmlabonne/NeuralDaredevil-8B-abliterated · int4Source: NanoGPTNot published by the provider$0.441cache read $0.2205$0.441

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

  • GitHub - mlabonne/mlabonne
    README 𝕏 Follow me on X · 🤗 Hugging Face · 💻 Blog · 📙 …README 𝕏 Follow me on X · 🤗 Hugging Face · 💻 Blog · 📙 LLM Engineer's Handbook Hi, I'm a Machine Learning Scientist, Author, Blogger, and LLM Developer. 💼 Projects The LLM Course : A popular cura…

    github.com

  • Maxime Labonne mlabonne
    Maxime Labonne mlabonne Hi, I'm a Machine Learning Scientist, Author, Blogger, and LLM Developer. My …Maxime Labonne mlabonne Hi, I'm a Machine Learning Scientist, Author, Blogger, and LLM Developer. My work at Liquid AI is to post-train our pre-trained LLMs with a custom architecture

    github.com

  • mlabonne (Maxime Labonne) · GitHub
    Achievement: Quickdraw Achievement: YOLO Achievement: Starstruck x4 Block or report user Overview Repositories 23 Projects …Achievement: Quickdraw Achievement: YOLO Achievement: Starstruck x4 Block or report user Overview Repositories 23 Projects Packages Stars 160 mlabonne / README .md 𝕏 Follow me on X · 🤗 Hugging Face…

    git.832008.xyz

  • mlabonne (Maxime Labonne) - Hugging Face
    Maxime Labonne's picture TFLOPS icon 37.3 TFLOPS Maxime Labonne PRO mlabonne LiquidAI 503 179 1238 …Maxime Labonne's picture TFLOPS icon 37.3 TFLOPS Maxime Labonne PRO mlabonne LiquidAI 503 179 1238 Follow victor's profile picture mjbuehler's profile picture fpaupier's profile picture 8,200 followe…

    huggingface.co

  • mlabonne (Maxime Labonne)
    mlabonne (Maxime Labonne) Post-training, model editing, quantization. Maxime Labonne PRO maxime-labonne AI & ML interests …mlabonne (Maxime Labonne) Post-training, model editing, quantization. Maxime Labonne PRO maxime-labonne AI & ML interests Post-training, model editing, quantization. Deploy local agents

    huggingface.co

  • mlabonne (Maxime Labonne)
    Maxime Labonne's picture TFLOPS icon 37.3 TFLOPS Maxime Labonne PRO mlabonne LiquidAI 517 180 1242 …Maxime Labonne's picture TFLOPS icon 37.3 TFLOPS Maxime Labonne PRO mlabonne LiquidAI 517 180 1242 Follow mattmcclean's profile picture Rothfeld's profile picture kol-sergei's profile picture 8,260 f…

    huggingface.co

  • mlabonne (Maxime Labonne)
    Maxime Labonne's picture TFLOPS icon 37.3 TFLOPS Maxime Labonne PRO mlabonne LiquidAI 517 181 1245 …Maxime Labonne's picture TFLOPS icon 37.3 TFLOPS Maxime Labonne PRO mlabonne LiquidAI 517 181 1245 Follow Stanlito's profile picture vikashkodati's profile picture tuanio's profile picture 8,262 foll…

    huggingface.co

  • mlabonne (Maxime Labonne)
    from my book. All the code is freely available at https://github.com/PacktPublishing/LLM-Engineers-Handbook mlabonne/TwinLlama-3.1-8B Text Generation · …from my book. All the code is freely available at https://github.com/PacktPublishing/LLM-Engineers-Handbook mlabonne/TwinLlama-3.1-8B Text Generation · 8B · Updated Oct 6, 2024 · 129 · 33 mlabonne/Tw…

    huggingface.co

  • mlabonne (Maxime Labonne)
    prompts mlabonne Sep 7, 2024 Paused Agents 7 #### TwinLlama-3.1-8B 👥 Generate text responses to …prompts mlabonne Sep 7, 2024 Paused Agents 7 #### TwinLlama-3.1-8B 👥 Generate text responses to user queries mlabonne Aug 22, 2024 Paused Agents 5 #### FineLlama-3.1-8B 🍷 mlabonne Jul 29, 2024 Paus…

    huggingface.co

  • mlabonne/Omnarch-7B · Hugging Face
    tokenizer = AutoTokenizer.from_pretrained("mlabonne/Omnarch-7B") model = AutoModelForCausalLM.from_pretrained("mlabonne/Omnarch-7B") Notebooks Google Colab Kaggle Local Apps Settings vLLM How …tokenizer = AutoTokenizer.from_pretrained("mlabonne/Omnarch-7B") model = AutoModelForCausalLM.from_pretrained("mlabonne/Omnarch-7B") Notebooks Google Colab Kaggle Local Apps Settings vLLM How to use …

    huggingface.co

Also known as: mlabonne/neuraldaredevil-8b-abliterated

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