metadata

license: apache-2.0
inference: false
datasets:
  - CohereForAI/xP3x
  - CohereForAI/aya_dataset
  - CohereForAI/aya_collection
  - DataProvenanceInitiative/Commercially-Verified-Licenses
  - CohereForAI/aya_evaluation_suite
language:
  - afr
  - amh
  - ara
  - aze
  - bel
  - ben
  - bul
  - cat
  - ceb
  - ces
  - cym
  - dan
  - deu
  - ell
  - eng
  - epo
  - est
  - eus
  - fin
  - fil
  - fra
  - fry
  - gla
  - gle
  - glg
  - guj
  - hat
  - hau
  - heb
  - hin
  - hun
  - hye
  - ibo
  - ind
  - isl
  - ita
  - jav
  - jpn
  - kan
  - kat
  - kaz
  - khm
  - kir
  - kor
  - kur
  - lao
  - lav
  - lat
  - lit
  - ltz
  - mal
  - mar
  - mkd
  - mlg
  - mlt
  - mon
  - mri
  - msa
  - mya
  - nep
  - nld
  - nor
  - nso
  - nya
  - ory
  - pan
  - pes
  - pol
  - por
  - pus
  - ron
  - rus
  - sin
  - slk
  - slv
  - smo
  - sna
  - snd
  - som
  - sot
  - spa
  - sqi
  - srp
  - sun
  - swa
  - swe
  - tam
  - tel
  - tgk
  - tha
  - tur
  - twi
  - ukr
  - urd
  - uzb
  - vie
  - xho
  - yid
  - yor
  - zho
  - zul
metrics:
  - accuracy
  - bleu

Aya-101-GGUF

This repo contains GGUF format model files for Cohere's Aya-101 model

Quantized using Huggingface's candle framework

How to use with Candle quantized T5 example

Visit the candle T5 example for more detailed instruction

Clone candle repo:

git clone https://github.com/huggingface/candle.git
cd candle/candle-examples

Run the following command:

cargo run --example quantized-t5 --release  -- \
  --model-id "kcoopermiller/aya-101-GGUF" \
  --weight-file "aya-101.Q2_K.gguf" \
  --config-file "config.json" \
  --prompt "भारत में इतनी सारी भाषाएँ क्यों हैं?" \
  --temperature 0

Note: this runs on CPU

Available weight files:

aya-101.Q2_K.gguf
aya-101.Q3_K.gguf
aya-101.Q4_0.gguf
aya-101.Q4_1.gguf
aya-101.Q4_K.gguf
aya-101.Q5_0.gguf
aya-101.Q5_1.gguf
aya-101.Q5_K.gguf
aya-101.Q6_K.gguf
aya-101.Q8_0.gguf
aya-101.Q8_1.gguf
aya-101.Q8_K.gguf (not supported on candle yet)