Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-license: mit
+license: openrail
 datasets:
 - irds/codesearchnet
 - giganticode/java-cmpx-v1
@@ -88,6 +88,34 @@ datasets:
 - rombodawg/LosslessMegaCodeTrainingV3_MINI
 - BelleGroup/multiturn_chat_0.8M
 - smangrul/code-chat-assistant-v1
+- goendalf666/sales-textbook_for_convincing_and_selling
+- readerbench/ConversationalAgent-Ro
+- beurkinger/autotrain-data-human-action-recognition
+- jpwahle/autoencoder-paraphrase-dataset
+- jpwahle/autoregressive-paraphrase-dataset
+- teknium/GPT4-LLM-Cleaned
+- Anthropic/model-written-evals
+- openai_humaneval
+- kye/all-google-ai-python-code
+- kye/all-openai-github-code
+- EleutherAI/lambada_openai
+- CShorten/ML-ArXiv-Papers
+- WaltonFuture/InstructionGPT-4
+- open-llm-leaderboard/details_AIDC-ai-business__Marcoroni-70B
+- seansullivan/INT-Business-Syllabus
+- theoldmandthesea/17k_business_book
+- SunRise228/business-doc
+- gauravshrm211/VC-startup-evaluation-for-investment
+- TuningAI/Startups_V1
+- TuningAI/Startups_V2
+- AdiOO7/llama-2-finance
+- scillm/scientific_papers
+- gokuls/wiki_book_corpus_complete_processed_bert_dataset
+- the_pile_books3
+- go_emotions
+- yizhongw/self_instruct
+- codeparrot/self-instruct-starcoder
+- Amani27/massive_translation_dataset
 language:
 - en
 - it
@@ -98,8 +126,11 @@ language:
 - ro
 - el
 - ja
-- ch
 - zh
+- ga
+- cy
+- gd
+- de
 metrics:
 - accuracy
 - bertscore
@@ -109,9 +140,11 @@ metrics:
 - brier_score
 - cer
 - chrf
+- charcut_mt
+- bleurt
 tags:
 - code
-- text-generation-inference
+- conversational
 library_name: transformers
 pipeline_tag: conversational
 ---
@@ -122,7 +155,7 @@ pipeline_tag: conversational
 
 **Model type:** Large language model
 
-**Model size:** 175B parameters
+**Model size:** 248B parameters
 
 **Intended use:** Aiden T5 is a large language model that can be used for a variety of tasks, including text generation, translation, summarization, and question answering. It is still under development, but it has learned to perform many kinds of tasks surprisingly well.
 
@@ -137,11 +170,10 @@ pipeline_tag: conversational
 **How to use Aiden T5:** Aiden T5 can be used through the Hugging Face Hub. To use Aiden T5, simply create a new project and select the Aiden T5 model. You can then use Aiden T5 to generate text, translate languages, summarize text, and answer questions.
 
 
-The number of parameters in a machine learning model is a measure of its complexity. Aiden T5 has 175B parameters, which makes it one of the largest and most complex language models ever created.
+The number of parameters in a machine learning model is a measure of its complexity. Aiden T5 has 248B parameters, which makes it one of the largest and most complex language models ever created.
 
 The number of parameters is important because it affects the model's ability to learn from data. A model with more parameters can learn more complex relationships between the input and output data. However, a model with too many parameters can be overfitting, which means that it learns the training data too well and does not generalize well to new data.
 
 The developers of Aiden T5 have carefully tuned the number of parameters to achieve a good balance between learning and generalization. As a result, Aiden T5 is able to learn complex relationships from the training data and generalize well to new data.
 
-This is why Aiden T5 is able to perform many kinds of tasks surprisingly well, even though it is still under development.
-
+This is why Aiden T5 is able to perform many kinds of tasks surprisingly well, even though it is still under development.