Hugging Face's logo

tensorblock
/
Sailor-7B-Chat-GGUF

GGUF
multilingual
sea
sailor
sft
chat
instruction
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Sailor-7B-Chat-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
78b0982 verified
preview code
|
raw
history blame contribute delete
5.17 kB
metadata
language:
  - en
  - zh
  - id
  - th
  - vi
  - ms
  - lo
datasets:
  - CohereForAI/aya_dataset
  - CohereForAI/aya_collection
  - Open-Orca/OpenOrca
tags:
  - multilingual
  - sea
  - sailor
  - sft
  - chat
  - instruction
  - TensorBlock
  - GGUF
widget:
  - text: 如何制作烤鱼？
    example_title: Chinese
  - text: How to bake fish?
    example_title: English
  - text: Bagaimana cara memanggang ikan?
    example_title: Malay
  - text: วิธีย่างปลา?
    example_title: Thai
  - text: Bagaimana membuat bakaran ikan?
    example_title: Indonesian
  - text: Làm thế nào để nướng cá?
    example_title: Vietnamese
license: apache-2.0
base_model: sail/Sailor-7B-Chat
TensorBlock

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

sail/Sailor-7B-Chat - GGUF

This repo contains GGUF format model files for sail/Sailor-7B-Chat.

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|>answer

Model file specification

Filename Quant type File Size Description
Sailor-7B-Chat-Q2_K.gguf Q2_K 3.104 GB smallest, significant quality loss - not recommended for most purposes
Sailor-7B-Chat-Q3_K_S.gguf Q3_K_S 3.569 GB very small, high quality loss
Sailor-7B-Chat-Q3_K_M.gguf Q3_K_M 3.919 GB very small, high quality loss
Sailor-7B-Chat-Q3_K_L.gguf Q3_K_L 4.218 GB small, substantial quality loss
Sailor-7B-Chat-Q4_0.gguf Q4_0 4.512 GB legacy; small, very high quality loss - prefer using Q3_K_M
Sailor-7B-Chat-Q4_K_S.gguf Q4_K_S 4.543 GB small, greater quality loss
Sailor-7B-Chat-Q4_K_M.gguf Q4_K_M 4.767 GB medium, balanced quality - recommended
Sailor-7B-Chat-Q5_0.gguf Q5_0 5.399 GB legacy; medium, balanced quality - prefer using Q4_K_M
Sailor-7B-Chat-Q5_K_S.gguf Q5_K_S 5.399 GB large, low quality loss - recommended
Sailor-7B-Chat-Q5_K_M.gguf Q5_K_M 5.531 GB large, very low quality loss - recommended
Sailor-7B-Chat-Q6_K.gguf Q6_K 6.342 GB very large, extremely low quality loss
Sailor-7B-Chat-Q8_0.gguf Q8_0 8.212 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/Sailor-7B-Chat-GGUF --include "Sailor-7B-Chat-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/Sailor-7B-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'