Hugging Face's logo

llmware
/
teknium-open-hermes-2.5-mistral-ov

OpenVINO
mistral
green
p7
llmware-chat
ov
Model card Files Community
Edit model card

teknium-open-hermes-2.5-mistral-ov

teknium-open-hermes-2.5-mistral-ov is an OpenVino int4 quantized version of teknium's popular open hermes finetune of mistral, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

teknium-open-hermes-2.5-mistral is a leading chat finetuned version of mistral 7b.

Model Description

  • Developed by: teknium
  • Quantized by: llmware
  • Model type: mistral-7b
  • Parameters: 7 billion
  • Model Parent: teknium/OpenHermes-2.5-Mistral-7B
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: General purpose chat
  • RAG Benchmark Accuracy Score: NA
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website

Downloads last month
9
Inference API
Inference API (serverless) has been turned off for this model.

Model tree for llmware/teknium-open-hermes-2.5-mistral-ov

Base model

mistralai/Mistral-7B-v0.1
Finetuned
teknium/OpenHermes-2.5-Mistral-7B
Quantized
(34)
this model

Collection including llmware/teknium-open-hermes-2.5-mistral-ov