Update from ToluClassics

README.md

@@ -0,0 +1,51 @@
+Hugging Face's logo
+---
+language: 
+- om
+- am
+- rw
+- rn
+- ha
+- ig
+- pcm
+- so
+- sw
+- ti
+- yo
+- multilingual
+- T5
+
+---
+# afriteva_base
+
+## Model desription
+
+AfriTeVa base is a sequence to sequence model pretrained on 10 African languages
+
+## Languages
+
+Afaan Oromoo(orm), Amharic(amh), Gahuza(gah), Hausa(hau), Igbo(igb), Nigerian Pidgin(pcm), Somali(som), Swahili(swa), Tigrinya(tig), Yoruba(yor)
+
+### More information on the model, dataset:
+
+### The model
+
+- 229M parameters encoder-decoder architecture (T5-like)
+- 12 layers, 12 attention heads and 512 token sequence length
+
+### The dataset
+
+- Multilingual: 10 African languages listed above
+- 143 Million Tokens (1GB of text data)
+- Tokenizer Vocabulary Size: 70,000 tokens
+
+## Training Procedure
+
+For information on training procedures, please refer to the AfriTeVa [paper](#) or [repository](https://github.com/castorini/afriteva)
+
+## BibTex entry and Citation info
+
+coming soon ...
+
+
+

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "/Users/mac/Documents/afriTeVa_Models/afrit5_large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 40103
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aee0d124ad16d361cf257ba20c678c289b0e87a93bee5b65f4b157c85c267bb
+size 2983489712

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "pad_token": "<pad>",
+    "extra_ids": 100,
+    "additional_special_tokens": [
+        "<extra_id_0>",
+        "<extra_id_1>",
+        "<extra_id_2>",
+        "<extra_id_3>",
+        "<extra_id_4>",
+        "<extra_id_5>",
+        "<extra_id_6>",
+        "<extra_id_7>",
+        "<extra_id_8>",
+        "<extra_id_9>",
+        "<extra_id_10>",
+        "<extra_id_11>",
+        "<extra_id_12>",
+        "<extra_id_13>",
+        "<extra_id_14>",
+        "<extra_id_15>",
+        "<extra_id_16>",
+        "<extra_id_17>",
+        "<extra_id_18>",
+        "<extra_id_19>",
+        "<extra_id_20>",
+        "<extra_id_21>",
+        "<extra_id_22>",
+        "<extra_id_23>",
+        "<extra_id_24>",
+        "<extra_id_25>",
+        "<extra_id_26>",
+        "<extra_id_27>",
+        "<extra_id_28>",
+        "<extra_id_29>",
+        "<extra_id_30>",
+        "<extra_id_31>",
+        "<extra_id_32>",
+        "<extra_id_33>",
+        "<extra_id_34>",
+        "<extra_id_35>",
+        "<extra_id_36>",
+        "<extra_id_37>",
+        "<extra_id_38>",
+        "<extra_id_39>",
+        "<extra_id_40>",
+        "<extra_id_41>",
+        "<extra_id_42>",
+        "<extra_id_43>",
+        "<extra_id_44>",
+        "<extra_id_45>",
+        "<extra_id_46>",
+        "<extra_id_47>",
+        "<extra_id_48>",
+        "<extra_id_49>",
+        "<extra_id_50>",
+        "<extra_id_51>",
+        "<extra_id_52>",
+        "<extra_id_53>",
+        "<extra_id_54>",
+        "<extra_id_55>",
+        "<extra_id_56>",
+        "<extra_id_57>",
+        "<extra_id_58>",
+        "<extra_id_59>",
+        "<extra_id_60>",
+        "<extra_id_61>",
+        "<extra_id_62>",
+        "<extra_id_63>",
+        "<extra_id_64>",
+        "<extra_id_65>",
+        "<extra_id_66>",
+        "<extra_id_67>",
+        "<extra_id_68>",
+        "<extra_id_69>",
+        "<extra_id_70>",
+        "<extra_id_71>",
+        "<extra_id_72>",
+        "<extra_id_73>",
+        "<extra_id_74>",
+        "<extra_id_75>",
+        "<extra_id_76>",
+        "<extra_id_77>",
+        "<extra_id_78>",
+        "<extra_id_79>",
+        "<extra_id_80>",
+        "<extra_id_81>",
+        "<extra_id_82>",
+        "<extra_id_83>",
+        "<extra_id_84>",
+        "<extra_id_85>",
+        "<extra_id_86>",
+        "<extra_id_87>",
+        "<extra_id_88>",
+        "<extra_id_89>",
+        "<extra_id_90>",
+        "<extra_id_91>",
+        "<extra_id_92>",
+        "<extra_id_93>",
+        "<extra_id_94>",
+        "<extra_id_95>",
+        "<extra_id_96>",
+        "<extra_id_97>",
+        "<extra_id_98>",
+        "<extra_id_99>"
+    ],
+    "special_tokens_map_file": null,
+    "name_or_path": "afrit5_tokenizers/afrit5_tokenizers",
+    "tokenizer_class": "T5Tokenizer"
+}