Hugging Face's logo

tensorblock
/
solar-megamerge-dare-10.7b-v1-GGUF

Text Generation
GGUF
PyTorch
English
dare
super mario merge
solar
Merge
TensorBlock
GGUF
Model card Files Community
solar-megamerge-dare-10.7b-v1-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
6745050 verified
preview code
|
raw
history blame contribute delete
5.27 kB
metadata
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
inference: false
tags:
  - dare
  - super mario merge
  - pytorch
  - solar
  - merge
  - TensorBlock
  - GGUF
base_model: martyn/solar-megamerge-dare-10.7b-v1
TensorBlock

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

martyn/solar-megamerge-dare-10.7b-v1 - GGUF

This repo contains GGUF format model files for martyn/solar-megamerge-dare-10.7b-v1.

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

Prompt template

Model file specification

Filename Quant type File Size Description
solar-megamerge-dare-10.7b-v1-Q2_K.gguf Q2_K 4.003 GB smallest, significant quality loss - not recommended for most purposes
solar-megamerge-dare-10.7b-v1-Q3_K_S.gguf Q3_K_S 4.665 GB very small, high quality loss
solar-megamerge-dare-10.7b-v1-Q3_K_M.gguf Q3_K_M 5.196 GB very small, high quality loss
solar-megamerge-dare-10.7b-v1-Q3_K_L.gguf Q3_K_L 5.651 GB small, substantial quality loss
solar-megamerge-dare-10.7b-v1-Q4_0.gguf Q4_0 6.072 GB legacy; small, very high quality loss - prefer using Q3_K_M
solar-megamerge-dare-10.7b-v1-Q4_K_S.gguf Q4_K_S 6.119 GB small, greater quality loss
solar-megamerge-dare-10.7b-v1-Q4_K_M.gguf Q4_K_M 6.462 GB medium, balanced quality - recommended
solar-megamerge-dare-10.7b-v1-Q5_0.gguf Q5_0 7.397 GB legacy; medium, balanced quality - prefer using Q4_K_M
solar-megamerge-dare-10.7b-v1-Q5_K_S.gguf Q5_K_S 7.397 GB large, low quality loss - recommended
solar-megamerge-dare-10.7b-v1-Q5_K_M.gguf Q5_K_M 7.598 GB large, very low quality loss - recommended
solar-megamerge-dare-10.7b-v1-Q6_K.gguf Q6_K 8.805 GB very large, extremely low quality loss
solar-megamerge-dare-10.7b-v1-Q8_0.gguf Q8_0 11.404 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/solar-megamerge-dare-10.7b-v1-GGUF --include "solar-megamerge-dare-10.7b-v1-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/solar-megamerge-dare-10.7b-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'