Merge branch 'main' of https://huggingface.co/ybelkada/flan-t5-large into main

README.md

@@ -62,9 +62,7 @@ language:
 - no
 
 tags:
-- summarization
-- translation
-- text-generation
+- text2text-generation
 
 datasets:
 - svakulenk0/qrecc
@@ -101,7 +99,7 @@ license: apache-2.0
 
 # TL;DR
 
-If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.  
+If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages. 
 As mentioned in the first few lines of the abstract : 
 >  Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints,1 which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
 
@@ -155,7 +153,7 @@ print(tokenizer.decode(outputs[0]))
 <summary> Click to expand </summary>
 
 ```python
-
+# pip install accelerate
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
 tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
@@ -178,6 +176,7 @@ print(tokenizer.decode(outputs[0]))
 <summary> Click to expand </summary>
 
 ```python
+# pip install accelerate
 import torch
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
@@ -199,7 +198,7 @@ print(tokenizer.decode(outputs[0]))
 <summary> Click to expand </summary>
 
 ```python
-# pip install bitsandbytes
+# pip install bitsandbytes accelerate
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
 tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
@@ -308,8 +307,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
   
   copyright = {Creative Commons Attribution 4.0 International}
 }
-```
-
-# Model Card Authors
-
-This model card was written by the team at Hugging Face.
+```

config.json

@@ -23,35 +23,6 @@
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "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: "
-    }
-  },
   "tie_word_embeddings": false,
   "transformers_version": "4.23.1",
   "use_cache": true,