Hugging Face's logo

tensorblock
/
X-ALMA-13B-Pretrain-GGUF

GGUF
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
X-ALMA-13B-Pretrain-GGUF / README.md
morriszms's picture
morriszms
Update README.md
edac28b verified
preview code
|
raw
history blame contribute delete
5.12 kB
metadata
license: mit
datasets:
  - oscar-corpus/OSCAR-2301
  - allenai/nllb
  - Helsinki-NLP/opus-100
language:
  - en
  - da
  - nl
  - de
  - is
  - 'no'
  - sc
  - af
  - ca
  - ro
  - gl
  - it
  - pt
  - es
  - bg
  - mk
  - sr
  - uk
  - ru
  - id
  - ms
  - th
  - vi
  - mg
  - fr
  - hu
  - el
  - cs
  - pl
  - lt
  - lv
  - ka
  - zh
  - ja
  - ko
  - fi
  - et
  - gu
  - hi
  - mr
  - ne
  - ur
  - az
  - kk
  - ky
  - tr
  - uz
  - ar
  - he
  - fa
base_model: haoranxu/X-ALMA-13B-Pretrain
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

haoranxu/X-ALMA-13B-Pretrain - GGUF

This repo contains GGUF format model files for haoranxu/X-ALMA-13B-Pretrain.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template 

<s>[INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]

Model file specification

Filename Quant type File Size Description
X-ALMA-13B-Pretrain-Q2_K.gguf Q2_K 4.521 GB smallest, significant quality loss - not recommended for most purposes
X-ALMA-13B-Pretrain-Q3_K_S.gguf Q3_K_S 5.270 GB very small, high quality loss
X-ALMA-13B-Pretrain-Q3_K_M.gguf Q3_K_M 5.903 GB very small, high quality loss
X-ALMA-13B-Pretrain-Q3_K_L.gguf Q3_K_L 6.454 GB small, substantial quality loss
X-ALMA-13B-Pretrain-Q4_0.gguf Q4_0 6.860 GB legacy; small, very high quality loss - prefer using Q3_K_M
X-ALMA-13B-Pretrain-Q4_K_S.gguf Q4_K_S 6.913 GB small, greater quality loss
X-ALMA-13B-Pretrain-Q4_K_M.gguf Q4_K_M 7.326 GB medium, balanced quality - recommended
X-ALMA-13B-Pretrain-Q5_0.gguf Q5_0 8.356 GB legacy; medium, balanced quality - prefer using Q4_K_M
X-ALMA-13B-Pretrain-Q5_K_S.gguf Q5_K_S 8.356 GB large, low quality loss - recommended
X-ALMA-13B-Pretrain-Q5_K_M.gguf Q5_K_M 8.596 GB large, very low quality loss - recommended
X-ALMA-13B-Pretrain-Q6_K.gguf Q6_K 9.946 GB very large, extremely low quality loss
X-ALMA-13B-Pretrain-Q8_0.gguf Q8_0 12.881 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/X-ALMA-13B-Pretrain-GGUF --include "X-ALMA-13B-Pretrain-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/X-ALMA-13B-Pretrain-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'