From original readme

Emollama-chat-7b is part of the EmoLLMs project, the first open-source large language model (LLM) series for comprehensive affective analysis with instruction-following capability. This model is finetuned based on the Meta LLaMA2-chat-7B foundation model and the full AAID instruction tuning data. The model can be used for affective classification tasks (e.g. sentimental polarity or categorical emotions), and regression tasks (e.g. sentiment strength or emotion intensity).

Usage

You can use the Emollama-chat-7b model in your Python project with the Hugging Face Transformers library. Here is a simple example of how to load the model:

from transformers import LlamaTokenizer, LlamaForCausalLM
tokenizer = LlamaTokenizer.from_pretrained('lzw1008/Emollama-chat-7b')
model = LlamaForCausalLM.from_pretrained('lzw1008/Emollama-chat-7b', device_map='auto')

In this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The device_map='auto' argument is used to automatically use the GPU if it's available.

Prompt examples

Emotion intensity

Human: 
Task: Assign a numerical value between 0 (least E) and 1 (most E) to represent the intensity of emotion E expressed in the text.
Text: @CScheiwiller can't stop smiling 😆😆😆
Emotion: joy
Intensity Score:

Assistant:
>>0.896

Sentiment strength

Human:
Task: Evaluate the valence intensity of the writer's mental state based on the text, assigning it a real-valued score from 0 (most negative) to 1 (most positive).
Text: Happy Birthday shorty. Stay fine stay breezy stay wavy @daviistuart 😘
Intensity Score:

Assistant:
>>0.879

Sentiment classification

Human:
Task: Categorize the text into an ordinal class that best characterizes the writer's mental state, considering various degrees of positive and negative sentiment intensity. 3: very positive mental state can be inferred. 2: moderately positive mental state can be inferred. 1: slightly positive mental state can be inferred. 0: neutral or mixed mental state can be inferred. -1: slightly negative mental state can be inferred. -2: moderately negative mental state can be inferred. -3: very negative mental state can be inferred
Text: Beyoncé resentment gets me in my feelings every time. 😩
Intensity Class:

Assistant:
>>-3: very negative emotional state can be inferred

Emotion classification

Human:
Task: Categorize the text's emotional tone as either 'neutral or no emotion' or identify the presence of one or more of the given emotions (anger, anticipation, disgust, fear, joy, love, optimism, pessimism, sadness, surprise, trust).
Text: Whatever you decide to do make sure it makes you #happy.
This text contains emotions:

Assistant:
>>joy, love, optimism

The task description can be adjusted according to the specific task.