Hugging Face's logo

tensorblock
/
Meltemi-7B-Instruct-v1-GGUF

Text Generation
GGUF
Greek
English
finetuned
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Meltemi-7B-Instruct-v1-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
acb8151 verified
preview code
|
raw
history blame contribute delete
4.99 kB
metadata
license: apache-2.0
language:
  - el
  - en
tags:
  - finetuned
  - TensorBlock
  - GGUF
inference: true
pipeline_tag: text-generation
base_model: ilsp/Meltemi-7B-Instruct-v1
TensorBlock

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

ilsp/Meltemi-7B-Instruct-v1 - GGUF

This repo contains GGUF format model files for ilsp/Meltemi-7B-Instruct-v1.

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

Prompt template 

<|system|>
{system_prompt}</s>
<|user|>
{prompt}</s>
<|assistant|>

Model file specification

Filename Quant type File Size Description
Meltemi-7B-Instruct-v1-Q2_K.gguf Q2_K 2.859 GB smallest, significant quality loss - not recommended for most purposes
Meltemi-7B-Instruct-v1-Q3_K_S.gguf Q3_K_S 3.317 GB very small, high quality loss
Meltemi-7B-Instruct-v1-Q3_K_M.gguf Q3_K_M 3.671 GB very small, high quality loss
Meltemi-7B-Instruct-v1-Q3_K_L.gguf Q3_K_L 3.974 GB small, substantial quality loss
Meltemi-7B-Instruct-v1-Q4_0.gguf Q4_0 4.277 GB legacy; small, very high quality loss - prefer using Q3_K_M
Meltemi-7B-Instruct-v1-Q4_K_S.gguf Q4_K_S 4.308 GB small, greater quality loss
Meltemi-7B-Instruct-v1-Q4_K_M.gguf Q4_K_M 4.537 GB medium, balanced quality - recommended
Meltemi-7B-Instruct-v1-Q5_0.gguf Q5_0 5.181 GB legacy; medium, balanced quality - prefer using Q4_K_M
Meltemi-7B-Instruct-v1-Q5_K_S.gguf Q5_K_S 5.181 GB large, low quality loss - recommended
Meltemi-7B-Instruct-v1-Q5_K_M.gguf Q5_K_M 5.315 GB large, very low quality loss - recommended
Meltemi-7B-Instruct-v1-Q6_K.gguf Q6_K 6.141 GB very large, extremely low quality loss
Meltemi-7B-Instruct-v1-Q8_0.gguf Q8_0 7.954 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/Meltemi-7B-Instruct-v1-GGUF --include "Meltemi-7B-Instruct-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/Meltemi-7B-Instruct-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'