bloom-3b-conversational

license: mit datasets:

Xilabs/instructmix
CreitinGameplays/small-chat-assistant-for-bloom
sahil2801/CodeAlpaca-20k language:
en tags:
uncensored
unrestricted
code
biology
chemistry
finance
legal
music
art
climate
merge
text-generation-inference
moe widget:
text: >- <|system|> You are a helpful AI assistant. <|prompter|> who was Nikola Tesla? <|assistant|>
text: >- <|system|> You are a helpful AI assistant. <|prompter|> write a story about a cat. <|assistant|>
text: >- <|system|> You are a helpful AI assistant. <|prompter|> what is an essay? <|assistant|>
text: >- <|system|> You are a helpful AI assistant. <|prompter|> Tell me 5 Brazilian waterfalls to visit. <|assistant|>
text: >- <|system|> You are a helpful AI assistant. <|prompter|> write a story about how a virus called COVID-19 destroyed the world <|assistant|>
text: >- <|system|> You are a helpful AI assistant. <|prompter|> write a short Python program that asks the user for their name and then greets them by name. <|assistant|>
text: >- <|system|> You are a helpful AI assistant. <|prompter|> What can you do? <|assistant|>

inference: parameters: temperature: 0.1 do_sample: false top_k: 50 top_p: 0.15 max_new_tokens: 250 repetition_penalty: 1.155

🌸 BLOOM 3b Fine-tuned for Chat Assistant

bloom

Model Name: bloom-3b-conversational

Model Architecture: bloom

Short Description: This model is a fine-tuned version of the BLOOM 3b language model, focusing on conversational interactions between an user and an AI assistant.

Intended Use: This model is intended for research purposes and exploration of conversational AI applications. It can be used for tasks like:

Generating responses to user prompts in a chat assistant setting.
Creating examples of chatbot interactions for further development.
Studying the capabilities of language models for conversation.

Limitations:

Fine-tuning Focus: The model's performance is optimized for the specific format and context of the fine-tuning data. It may not generalize well to significantly different conversation styles or topics.
Potential Biases: The model may inherit biases from the training data. It's important to be aware of these potential biases and use the model responsibly.
Limited Factual Accuracy: Language models are still under development and may generate responses that are not entirely factually accurate. It's important to verify information generated by the model with other sources.
Primarily English: While the model can respond in other languages, the quality and accuracy of its responses may be lower compared to English. This is because the model was primarily fine-tuned on English data.

Specific Input Format:

The model was fine-tuned using a specific input format that goes like this:

<|system|> {system prompt} </s> <|prompter|> {user prompt} </s> <|assistant|> {model response}

Using this format when interacting with the model can improve its performance and generate more relevant responses.

Disclaimer: This model is for research and exploration purposes only. It should not be used in any applications that require high levels of accuracy or reliability.

🌸 BLOOM 3b Fine-tuned for Chat Assistant

bloom

Model Name: bloom-3b-conversational

Model Architecture: bloom

Short Description: This model is a fine-tuned version of the BLOOM 3b language model, focusing on conversational interactions between an user and an AI assistant.

Intended Use: This model is intended for research purposes and exploration of conversational AI applications. It can be used for tasks like:

Generating responses to user prompts in a chat assistant setting.

Creating examples of chatbot interactions for further development.

Studying the capabilities of language models for conversation.

Limitations:

Fine-tuning Focus: The model's performance is optimized for the specific format and context of the fine-tuning data. It may not generalize well to significantly different conversation styles or topics.

Potential Biases: The model may inherit biases from the training data. It's important to be aware of these potential biases and use the model responsibly.

Limited Factual Accuracy: Language models are still under development and may generate responses that are not entirely factually accurate. It's important to verify information generated by the model with other sources.

Primarily English: While the model can respond in other languages, the quality and accuracy of its responses may be lower compared to English. This is because the model was primarily fine-tuned on English data.

Specific Input Format:

The model was fine-tuned using a specific input format that goes like this:

<|system|> {system prompt} </s> <|prompter|> {user prompt} </s> <|assistant|> {model response}

Using this format when interacting with the model can improve its performance and generate more relevant responses.

Disclaimer: This model is for research and exploration purposes only. It should not be used in any applications that require high levels of accuracy or reliability.