Edit model card

Hermes-2-Pro-Mistral-7B-iMat-GGUF

Source Model: NousResearch/Hermes-2-Pro-Mistral-7B

Quantized with llama.cpp commit 46acb3676718b983157058aecf729a2064fc7d34

Imatrix was generated from the f16 gguf via this command:

./imatrix -c 512 -m $out_path/$base_quant_name -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat

Using the dataset from here

Downloads last month: 191

GGUF

Model size

7.24B params

Architecture

llama

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API

Unable to determine this model's library. Check the docs .

Model tree for qwp4w3hyb/Hermes-2-Pro-Mistral-7B-iMat-GGUF

Base model

mistralai/Mistral-7B-v0.1

Finetuned

NousResearch/Hermes-2-Pro-Mistral-7B

Quantized

(16)

this model

Dataset used to train qwp4w3hyb/Hermes-2-Pro-Mistral-7B-iMat-GGUF

Evaluation results

Metadata error: specify a dataset to view leaderboard