Upload 5 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+aya-101.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,153 @@
 ---
 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](https://huggingface.co/CohereForAI/aya-101) model
+
+Quantized using Huggingface's [candle](https://github.com/huggingface/candle) framework
+
+## How to use with Candle
+Visit the [candle T5 example](https://github.com/huggingface/candle/tree/main/candle-examples/examples/quantized-t5) for more detailed instruction
+
+Clone candle repo:
+```bash
+git clone https://github.com/huggingface/candle.git
+cd candle/candle-examples
+```
+Run the following command:
+```bash
+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
+```
+
+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

aya-101.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b33b0fe80bc6abb65e20c733bda0f7406674c300871bbd7622330fa54f8ab3
+size 4241619232

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/home/patrick/t5/mt5-xxl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a036c0dfd2d80e1202a7e2961aeee653ff63d67cd369b155c78a6e2003a390
+size 16330562

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}