|
--- |
|
base_model: Nous-Hermes-2-Mixtral-8x7B-DPO |
|
license: apache-2.0 |
|
tags: |
|
- Mixtral |
|
- instruct |
|
- finetune |
|
- chatml |
|
- DPO |
|
- RLHF |
|
- gpt4 |
|
- synthetic data |
|
- distillation |
|
model-index: |
|
- name: qwp4w3hyb/Nous-Hermes-2-Mixtral-8x7B-DPO-iMat-GGUF |
|
results: [] |
|
language: |
|
- en |
|
datasets: |
|
- teknium/OpenHermes-2.5 |
|
--- |
|
|
|
# Nous-Hermes-2-Mixtral-8x7B-DPO-iMat-GGUF |
|
|
|
Source Model: [NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO) |
|
Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [46acb3676718b983157058aecf729a2064fc7d34](https://github.com/ggerganov/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](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) |
|
|
|
|
