kcoopermiller commited on
Commit
954769e
1 Parent(s): a75891d

Upload 5 files

Browse files
Files changed (6) hide show
  1. .gitattributes +2 -0
  2. README.md +150 -0
  3. aya-101.Q2_K.gguf +3 -0
  4. config.json +32 -0
  5. tokenizer.json +3 -0
  6. tokenizer_config.json +38 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ aya-101.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,153 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ inference: false
4
+ datasets:
5
+ - CohereForAI/xP3x
6
+ - CohereForAI/aya_dataset
7
+ - CohereForAI/aya_collection
8
+ - DataProvenanceInitiative/Commercially-Verified-Licenses
9
+ - CohereForAI/aya_evaluation_suite
10
+ language:
11
+ - afr
12
+ - amh
13
+ - ara
14
+ - aze
15
+ - bel
16
+ - ben
17
+ - bul
18
+ - cat
19
+ - ceb
20
+ - ces
21
+ - cym
22
+ - dan
23
+ - deu
24
+ - ell
25
+ - eng
26
+ - epo
27
+ - est
28
+ - eus
29
+ - fin
30
+ - fil
31
+ - fra
32
+ - fry
33
+ - gla
34
+ - gle
35
+ - glg
36
+ - guj
37
+ - hat
38
+ - hau
39
+ - heb
40
+ - hin
41
+ - hun
42
+ - hye
43
+ - ibo
44
+ - ind
45
+ - isl
46
+ - ita
47
+ - jav
48
+ - jpn
49
+ - kan
50
+ - kat
51
+ - kaz
52
+ - khm
53
+ - kir
54
+ - kor
55
+ - kur
56
+ - lao
57
+ - lav
58
+ - lat
59
+ - lit
60
+ - ltz
61
+ - mal
62
+ - mar
63
+ - mkd
64
+ - mlg
65
+ - mlt
66
+ - mon
67
+ - mri
68
+ - msa
69
+ - mya
70
+ - nep
71
+ - nld
72
+ - nor
73
+ - nso
74
+ - nya
75
+ - ory
76
+ - pan
77
+ - pes
78
+ - pol
79
+ - por
80
+ - pus
81
+ - ron
82
+ - rus
83
+ - sin
84
+ - slk
85
+ - slv
86
+ - smo
87
+ - sna
88
+ - snd
89
+ - som
90
+ - sot
91
+ - spa
92
+ - sqi
93
+ - srp
94
+ - sun
95
+ - swa
96
+ - swe
97
+ - tam
98
+ - tel
99
+ - tgk
100
+ - tha
101
+ - tur
102
+ - twi
103
+ - ukr
104
+ - urd
105
+ - uzb
106
+ - vie
107
+ - xho
108
+ - yid
109
+ - yor
110
+ - zho
111
+ - zul
112
+ metrics:
113
+ - accuracy
114
+ - bleu
115
  ---
116
+
117
+ # Aya-101-GGUF
118
+
119
+ This repo contains GGUF format model files for Cohere's [Aya-101](https://huggingface.co/CohereForAI/aya-101) model
120
+
121
+ Quantized using Huggingface's [candle](https://github.com/huggingface/candle) framework
122
+
123
+ ## How to use with Candle
124
+ Visit the [candle T5 example](https://github.com/huggingface/candle/tree/main/candle-examples/examples/quantized-t5) for more detailed instruction
125
+
126
+ Clone candle repo:
127
+ ```bash
128
+ git clone https://github.com/huggingface/candle.git
129
+ cd candle/candle-examples
130
+ ```
131
+ Run the following command:
132
+ ```bash
133
+ cargo run --example quantized-t5 --release -- \
134
+ --model-id "kcoopermiller/aya-101-GGUF" \
135
+ --weight-file "aya-101.Q2_K.gguf" \
136
+ --config-file "config.json" \
137
+ --prompt "भारत में इतनी सारी भाषाएँ क्यों हैं?" \
138
+ --temperature 0
139
+ ```
140
+
141
+ Available weight files:
142
+ - aya-101.Q2_K.gguf
143
+ - aya-101.Q3_K.gguf
144
+ - aya-101.Q4_0.gguf
145
+ - aya-101.Q4_1.gguf
146
+ - aya-101.Q4_K.gguf
147
+ - aya-101.Q5_0.gguf
148
+ - aya-101.Q5_1.gguf
149
+ - aya-101.Q5_K.gguf
150
+ - aya-101.Q6_K.gguf
151
+ - aya-101.Q8_0.gguf
152
+ - aya-101.Q8_1.gguf
153
+ - aya-101.Q8_K.gguf
aya-101.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b33b0fe80bc6abb65e20c733bda0f7406674c300871bbd7622330fa54f8ab3
3
+ size 4241619232
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/patrick/t5/mt5-xxl",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "transformers_version": "4.37.2",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a036c0dfd2d80e1202a7e2961aeee653ff63d67cd369b155c78a6e2003a390
3
+ size 16330562
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<pad>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }