Koboldai

41 indexed models

41 matching models

KoboldAI/GPT-NeoX-20B-Erebus

vertexAI/publishers/hf-koboldai/models/gpt-neox-20b-erebus@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 41.263%

KoboldAI/GPT-NeoX-20B-Skein

huggingface/KoboldAI/GPT-NeoX-20B-Skein

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 41.098%

KoboldAI/LLaMA2-13B-Estopia

huggingface/KoboldAI/LLaMA2-13B-Estopia

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 57.27%

KoboldAI/LLaMA2-13B-Holomax

azureFoundry/HuggingFace/koboldai-llama2-13b-holomax@1

`KoboldAI/LLaMA2-13B-Holomax` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/KoboldAI/LLaMA2-13B-Holomax) - [Text Generation Inference Documenta

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 54.518%

KoboldAI/LLaMA2-13B-Psyfighter2

huggingface/KoboldAI/LLaMA2-13B-Psyfighter2

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 54.656%

KoboldAI/LLaMA2-13B-Tiefighter

vertexAI/publishers/hf-koboldai/models/llama2-13b-tiefighter@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 54.513%

Inference prices

  • Published price : $0.10 / input_tokens_per_million · deepInfra ↗
  • Published price : $0.10 / output_tokens_per_million · deepInfra ↗

KoboldAI/Mistral-7B-Erebus-v3

huggingface/KoboldAI/Mistral-7B-Erebus-v3

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 56.821%

KoboldAI/Mistral-7B-Holodeck-1

huggingface/KoboldAI/Mistral-7B-Holodeck-1

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 59.557%

KoboldAI/OPT-13B-Erebus

vertexAI/publishers/hf-koboldai/models/opt-13b-erebus@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 39.606%

KoboldAI/OPT-13B-Nerybus-Mix

huggingface/KoboldAI/OPT-13B-Nerybus-Mix

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 39.605%

KoboldAI/OPT-13B-Nerys-v2

huggingface/KoboldAI/OPT-13B-Nerys-v2

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 39.528%

KoboldAI/OPT-2.7B-Erebus

azureFoundry/HuggingFace/koboldai-opt-2.7b-erebus@8

`KoboldAI/OPT-2.7B-Erebus` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biase

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 36.96%

KoboldAI/OPT-2.7B-Nerybus-Mix

huggingface/KoboldAI/OPT-2.7B-Nerybus-Mix

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 36.879%

KoboldAI/OPT-2.7B-Nerys-v2

huggingface/KoboldAI/OPT-2.7B-Nerys-v2

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 36.752%

KoboldAI/OPT-30B-Erebus

huggingface/KoboldAI/OPT-30B-Erebus

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 38.531%

KoboldAI/OPT-350M-Erebus

huggingface/KoboldAI/OPT-350M-Erebus

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 30.139%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace