Hugging Face's logo

tensorblock
/
llama-7b-finnish-instruct-v0.2-GGUF

Text Generation
Transformers
GGUF
finnish
llama
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
llama-7b-finnish-instruct-v0.2-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
2db38c0 verified
preview code
|
raw
history blame contribute delete
5.31 kB
metadata
library_name: transformers
license: apache-2.0
tags:
  - finnish
  - llama
  - TensorBlock
  - GGUF
inference: true
pipeline_tag: text-generation
base_model: Finnish-NLP/llama-7b-finnish-instruct-v0.2
TensorBlock

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

Finnish-NLP/llama-7b-finnish-instruct-v0.2 - GGUF

This repo contains GGUF format model files for Finnish-NLP/llama-7b-finnish-instruct-v0.2.

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
llama-7b-finnish-instruct-v0.2-Q2_K.gguf Q2_K 2.686 GB smallest, significant quality loss - not recommended for most purposes
llama-7b-finnish-instruct-v0.2-Q3_K_S.gguf Q3_K_S 3.114 GB very small, high quality loss
llama-7b-finnish-instruct-v0.2-Q3_K_M.gguf Q3_K_M 3.464 GB very small, high quality loss
llama-7b-finnish-instruct-v0.2-Q3_K_L.gguf Q3_K_L 3.763 GB small, substantial quality loss
llama-7b-finnish-instruct-v0.2-Q4_0.gguf Q4_0 4.009 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama-7b-finnish-instruct-v0.2-Q4_K_S.gguf Q4_K_S 4.040 GB small, greater quality loss
llama-7b-finnish-instruct-v0.2-Q4_K_M.gguf Q4_K_M 4.265 GB medium, balanced quality - recommended
llama-7b-finnish-instruct-v0.2-Q5_0.gguf Q5_0 4.852 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama-7b-finnish-instruct-v0.2-Q5_K_S.gguf Q5_K_S 4.852 GB large, low quality loss - recommended
llama-7b-finnish-instruct-v0.2-Q5_K_M.gguf Q5_K_M 4.983 GB large, very low quality loss - recommended
llama-7b-finnish-instruct-v0.2-Q6_K.gguf Q6_K 5.747 GB very large, extremely low quality loss
llama-7b-finnish-instruct-v0.2-Q8_0.gguf Q8_0 7.443 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/llama-7b-finnish-instruct-v0.2-GGUF --include "llama-7b-finnish-instruct-v0.2-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/llama-7b-finnish-instruct-v0.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'