その後、下にある「Generate NEW API KEY」をクリックすれば、新しいAPIキーが生成される。注意サインにあるように、APIを再度表示することはできないので、コピー&ペーストで、管理が容易な場所に格納することが望ましい。またAPIキーは、当該アカウントに紐づくもので、有料ティアでは、モデル利用料に直結するため厳重に管理することが求められる。
次にこのAPIキーを先ほど作成した.envファイルに格納する。
ステップ5:Pythonスクリプトと実行
APIキーを.envに格納した後、もう一度SambaNova Cloudページに行き、オレンジ色の「View API Curl」ボタンをクリックする。
(venv) genhosoya@Gens-Mac-mini sambanova % /Users/genhosoya/sambanova/venv/bin/python /Users/genhosoya/sambanova/main.py
Here are some examples of Large Language Models (LLMs):
1. **BERT (Bidirectional Encoder Representations from Transformers)**: Developed by Google, BERT is a pre-trained language model that uses a multi-layer bidirectional transformer encoder to generate contextualized representations of words in a sentence.
2. **RoBERTa (Robustly Optimized BERT Pretraining Approach)**: Developed by Facebook AI, RoBERTa is a variant of BERT that uses a different approach to pre-training and has achieved state-of-the-art results on several natural language processing (NLP) benchmarks.
3. **Longformer**: Developed by Google, Longformer is a type of transformer model that is designed to handle longer input sequences than traditional transformer models.
4. **XLNet**: Developed by Google and Carnegie Mellon University, XLNet is a type of transformer model that uses a combination of autoencoding and autoregressive techniques to generate text.
5. **T5 (Text-to-Text Transfer Transformer)**: Developed by Google, T5 is a type of transformer model that is designed to handle a wide range of NLP tasks, including text classification, sentiment analysis, and machine translation.
6. **Llama**: Developed by Meta, Llama is an artificial intelligence model developed by Meta, designed to process and generate human-like language.
7. **ChatGPT**: Developed by OpenAI, ChatGPT is a chatbot that uses a variant of the GPT-3 model to generate human-like text in response to user input.
8. **GPT-3 (Generative Pre-trained Transformer 3)**: Developed by OpenAI, GPT-3 is a type of transformer model that uses a combination of pre-training and fine-tuning to generate human-like text.
9. **GPT-4 (Generative Pre-trained Transformer 4)**: Developed by OpenAI, GPT-4 is the fourth version of the company's GPT multimodal large language model.
(venv) genhosoya@Gens-Mac-mini sambanova %