lzw1008

/

Emollama-chat-7b

like 3

Thank you for making the models available.

I have a clarification question on replicability. I am using Emollama-chat-7b model. I get different results than what you have provided in the examples on your page.

For instance, consider the below prompt:

prompt = '''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:
'''

For the above prompt, I get the following results:
-2: moderately negative emotional state can be inferred

The response in your example for the same prompt is instead the following:
-3: very negative emotional state can be inferred

Not sure if this is expected or incorrect. Request your help.

sbs