Hugging Face's logo

tensorblock
/
salamandra-7b-instruct-GGUF

Text Generation
Transformers
GGUF
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
salamandra-7b-instruct-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
540ecf2 verified
preview code
|
raw
history blame contribute delete
5.79 kB
metadata
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
language:
  - bg
  - ca
  - code
  - cs
  - cy
  - da
  - de
  - el
  - en
  - es
  - et
  - eu
  - fi
  - fr
  - ga
  - gl
  - hr
  - hu
  - it
  - lt
  - lv
  - mt
  - nl
  - nn
  - \no
  - oc
  - pl
  - pt
  - ro
  - ru
  - sh
  - sk
  - sl
  - sr
  - sv
  - uk
datasets:
  - oscar-corpus/colossal-oscar-1.0
  - HuggingFaceFW/fineweb-edu
  - joelniklaus/eurlex_resources
  - joelito/legal-mc4
  - projecte-aina/CATalog
  - UFRGS/brwac
  - community-datasets/hrwac
  - danish-foundation-models/danish-gigaword
  - HiTZ/euscrawl
  - PleIAs/French-PD-Newspapers
  - PleIAs/French-PD-Books
  - AI-team-UoA/greek_legal_code
  - HiTZ/latxa-corpus-v1.1
  - allenai/peS2o
  - pile-of-law/pile-of-law
  - PORTULAN/parlamento-pt
  - hoskinson-center/proof-pile
  - togethercomputer/RedPajama-Data-1T
  - bigcode/starcoderdata
  - bjoernp/tagesschau-2018-2023
  - EleutherAI/the_pile_deduplicated
base_model: BSC-LT/salamandra-7b-instruct
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

BSC-LT/salamandra-7b-instruct - GGUF

This repo contains GGUF format model files for BSC-LT/salamandra-7b-instruct.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4658.

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
salamandra-7b-instruct-Q2_K.gguf Q2_K 3.305 GB smallest, significant quality loss - not recommended for most purposes
salamandra-7b-instruct-Q3_K_S.gguf Q3_K_S 3.755 GB very small, high quality loss
salamandra-7b-instruct-Q3_K_M.gguf Q3_K_M 4.048 GB very small, high quality loss
salamandra-7b-instruct-Q3_K_L.gguf Q3_K_L 4.300 GB small, substantial quality loss
salamandra-7b-instruct-Q4_0.gguf Q4_0 4.647 GB legacy; small, very high quality loss - prefer using Q3_K_M
salamandra-7b-instruct-Q4_K_S.gguf Q4_K_S 4.672 GB small, greater quality loss
salamandra-7b-instruct-Q4_K_M.gguf Q4_K_M 4.851 GB medium, balanced quality - recommended
salamandra-7b-instruct-Q5_0.gguf Q5_0 5.487 GB legacy; medium, balanced quality - prefer using Q4_K_M
salamandra-7b-instruct-Q5_K_S.gguf Q5_K_S 5.487 GB large, low quality loss - recommended
salamandra-7b-instruct-Q5_K_M.gguf Q5_K_M 5.592 GB large, very low quality loss - recommended
salamandra-7b-instruct-Q6_K.gguf Q6_K 6.380 GB very large, extremely low quality loss
salamandra-7b-instruct-Q8_0.gguf Q8_0 8.261 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/salamandra-7b-instruct-GGUF --include "salamandra-7b-instruct-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/salamandra-7b-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'