Hugging Face's logo

tensorblock
/
mixtral-megamerge-dare-8x7b-v2-GGUF

Text Generation
GGUF
PyTorch
English
dare
super mario merge
mixtral
Merge
TensorBlock
GGUF
conversational
Model card Files Community
mixtral-megamerge-dare-8x7b-v2-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
276863e verified
preview code
|
raw
history blame contribute delete
5.43 kB
metadata
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
inference: false
tags:
  - dare
  - super mario merge
  - pytorch
  - mixtral
  - merge
  - TensorBlock
  - GGUF
base_model: martyn/mixtral-megamerge-dare-8x7b-v2
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

martyn/mixtral-megamerge-dare-8x7b-v2 - GGUF

This repo contains GGUF format model files for martyn/mixtral-megamerge-dare-8x7b-v2.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
mixtral-megamerge-dare-8x7b-v2-Q2_K.gguf Q2_K 17.311 GB smallest, significant quality loss - not recommended for most purposes
mixtral-megamerge-dare-8x7b-v2-Q3_K_S.gguf Q3_K_S 20.433 GB very small, high quality loss
mixtral-megamerge-dare-8x7b-v2-Q3_K_M.gguf Q3_K_M 22.546 GB very small, high quality loss
mixtral-megamerge-dare-8x7b-v2-Q3_K_L.gguf Q3_K_L 24.170 GB small, substantial quality loss
mixtral-megamerge-dare-8x7b-v2-Q4_0.gguf Q4_0 26.444 GB legacy; small, very high quality loss - prefer using Q3_K_M
mixtral-megamerge-dare-8x7b-v2-Q4_K_S.gguf Q4_K_S 26.746 GB small, greater quality loss
mixtral-megamerge-dare-8x7b-v2-Q4_K_M.gguf Q4_K_M 28.448 GB medium, balanced quality - recommended
mixtral-megamerge-dare-8x7b-v2-Q5_0.gguf Q5_0 32.231 GB legacy; medium, balanced quality - prefer using Q4_K_M
mixtral-megamerge-dare-8x7b-v2-Q5_K_S.gguf Q5_K_S 32.231 GB large, low quality loss - recommended
mixtral-megamerge-dare-8x7b-v2-Q5_K_M.gguf Q5_K_M 33.230 GB large, very low quality loss - recommended
mixtral-megamerge-dare-8x7b-v2-Q6_K.gguf Q6_K 38.381 GB very large, extremely low quality loss
mixtral-megamerge-dare-8x7b-v2-Q8_0.gguf Q8_0 49.626 GB very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/mixtral-megamerge-dare-8x7b-v2-GGUF --include "mixtral-megamerge-dare-8x7b-v2-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/mixtral-megamerge-dare-8x7b-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'