lr1729
/

OpenHermes-2.5-Mistral-7B-imatrix

Model card Files Files and versions Community

Edit model card

GGUF quants of https://huggingface.co./teknium/OpenHermes-2.5-Mistral-7B with importance matrix calculations run on 20k_random_data.txt for improved perplexity.

Downloads last month: 250

GGUF

Model size

7.24B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

Inference API

Inference API (serverless) has been turned off for this model.

Model tree for lr1729/OpenHermes-2.5-Mistral-7B-imatrix

Base model

mistralai/Mistral-7B-v0.1

Finetuned

teknium/OpenHermes-2-Mistral-7B

Quantized

(5)

this model

Evaluation results

Metadata error: specify a dataset to view leaderboard