saidsef commited on
Commit
6055835
·
verified ·
1 Parent(s): 73a6959

chore: update model information

Browse files
Files changed (1) hide show
  1. README.md +34 -1
README.md CHANGED
@@ -18,4 +18,37 @@ If you already know T5, FLAN-T5 is just better at everything. For the same numbe
18
 
19
  >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.
20
 
21
- Disclaimer: Content from this model card has been written by the Hugging Face team, and parts of it were copy pasted from the [T5 model card](https://huggingface.co/google/flan-t5-small/blob/main/README.md).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
 
19
  >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.
20
 
21
+ Disclaimer: Content from this model card has been written by the Hugging Face team, and parts of it were copy pasted from the [T5 model card](https://huggingface.co/google/flan-t5-small/blob/main/README.md).
22
+
23
+ ## Limitations:
24
+
25
+ - The model may sometimes generate irrelevant keywords
26
+ - Performance may vary depending on the length and complexity of the input text
27
+ - For best results, use long clean texts
28
+ - Length limit is 512 tokens due to Flan-T5 architecture
29
+ - The model is trained on English text and may not perform well on other languages
30
+
31
+ ## Usage
32
+
33
+ ```python
34
+ # Use a pipeline as a high-level helper
35
+ from transformers import pipeline
36
+
37
+ pipe = pipeline("text2text-generation", model="saidsef/flan-t5-small-tuned-tech-docs")
38
+
39
+ # Load model directly
40
+ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
41
+
42
+ tokenizer = AutoTokenizer.from_pretrained("saidsef/flan-t5-small-tuned-tech-docs")
43
+ model = AutoModelForSeq2SeqLM.from_pretrained("saidsef/flan-t5-small-tuned-tech-docs")
44
+ ```
45
+
46
+ ## Framework versions
47
+ - Transformers 4.45.1
48
+ - Pytorch 2.4.1+cu121
49
+ - Datasets 3.0.1
50
+ - Tokenizers 0.20.0
51
+
52
+ ## Ethical Considerations
53
+
54
+ When using this model, consider the potential impact of automated keyword extraction on content creation and SEO practices. Ensure that the use of this model complies with relevant guidelines and does not contribute to the creation of misleading or spammy content.