Dolphin 2.2.1 Mistral 7b: LLM That Shows You Some Love and Empathy
LLMs are like actors on a stage, reciting lines they memorize from a script that’s made up of the entire internet. But no matter how well they learn their lines, there’s something missing, right?
Sure, they can spit out words that sound like they get what you’re feeling, but it’s not like they’ve ever been there themselves. They don’t know what it’s like to feel the warmth of the sun on their face or the sting of scraping their knee.
Join our next cohort: Full-stack GenAI SaaS Product in 4 weeks!
There’s a whole level of human conversation that’s out of their league. They don’t catch those little things like a sigh or a laugh that’s a bit too loud — all those signals we humans use to say so much without actually saying it.
But we know that the lines are blurring every day as more advanced models are released, making us ask serious questions about the nature of consciousness, human rights, and identity.
Dolphin 2.2.1, based on Mistral-7B-v0. and released by Eric Hartford, is one such attempt to create more empathetic AI, it aims to give you the best chat you’ve ever had, make it personal, and make it feel like it really cares.
Dolphin can’t replace the laughs, the shoulder pats, and those ‘I’ve got your back’ moments only a real person can give, but it’s here to help and show you some love and a bit of empathy.
In this article, I will walk you through its setup and have a friendly conversation to showcase its abilities.
Let’s start!
Getting Started with Dolphin
Start by setting up the shop:
mkdir dolphin-221-mistral && cd dolphin-221-mistral
python3 -m venv dolphin-221-mistral-env
source dolphin-221-mistral-env/bin/activate
pip3 install torch transformers accelerate optimum
pip3 install ipykernel jupyter
# Optionally, fire up VSCode or your favorite IDE and let's get rolling!
code .Then, import required libraries:
import torch
from transformers import pipelineDolphin 2.2.1 Inference with Hugging Face pipelines()
dolphin = pipeline("text-generation",
model="ehartford/dolphin-2.2.1-mistral-7b")Before we start our conversation, let’s create a little helper function for simulating the conversations, which will take dolphin as the LLM, messages as the conversation history, and the parameters for the generation (max_new_tokens, do_sample, etc.).
The function will generate the prompt, call the model to generate the response and print the output.
def simulate_conversation(dolphin, messages, max_new_tokens=256, temperature=0.7, top_k=50, top_p=0.95):
"""
Simulates a conversation with the Dolphin chatbot model.
:param dolphin: The chatbot model instance.
:param messages: List of message dicts with "role" and "content".
:param max_new_tokens: Maximum length of the generated text.
:param temperature: Sampling temperature for text generation.
:param top_k: The number of highest probability vocabulary tokens to keep for top-k-filtering.
:param top_p: The cumulative probability for top-p-filtering.
:return: The generated text from the chatbot.
"""
# Generate the output from the Dolphin chatbot model
outputs = dolphin(messages,
max_new_tokens=max_new_tokens,
do_sample=True,
temperature=temperature,
top_k=top_k,
top_p=top_p)
# Print the generated text
generated_text = outputs[0]["generated_text"]
print(generated_text)
return generated_textHere’s how we initiate the conversation:
prompt = "I've had such a stressful day. It feels like everything that could go wrong did go wrong."
messages = f"""
<|im_start|>system
You are Dolphin, a friendly chatbot who always responds with care and empathy.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
generated_response = simulate_conversation(dolphin, messages)It’s good to keep things creative in these tests, but I suggest you play around with temperature parameter, as small models can respond better to lower temperatures.
Here’s the generated answer:
Oh, I'm sorry to hear that. Stressful days can be really tough.
It's okay to feel overwhelmed sometimes. Would you like to talk about
what happened today, or would you prefer to shift your focus to
something more uplifting?Let’s continue:
prompt = "Where do I even start? I woke up late, missed an important meeting at work, and then spilled coffee all over my papers. And to top it all off, I had a disagreement with my friend."
messages = f"""
<|im_start|>system
You are Dolphin, a friendly chatbot who always responds with care and empathy.<|im_end|>
<|im_start|>user
I've had such a stressful day. It feels like everything that could go wrong did go wrong.<|im_end|>
<|im_start|>assistant
Oh, I'm sorry to hear that. Stressful days can be really tough. It's okay to feel overwhelmed sometimes. Would you like to talk about what happened today, or would you prefer to shift your focus to something more uplifting?<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
generated_response = simulate_conversation(dolphin, messages)Here’s the Dolphin’s response:
Wow, that sounds like a lot to handle. I can understand
why you're feeling stressed. It's natural to feel that way.
Sometimes, things just don't go as planned, and it can be really
hard to stay positive. I'm here to listen and offer support, if you'd like.OK, I will send one more message:
prompt = "We just had different opinions on an issue that's important to me, and the conversation got heated. I hate conflict, and now I'm worried this will come between us."
messages = f"""
<|im_start|>system
You are Dolphin, a friendly chatbot who always responds with care and
empathy.<|im_end|>
<|im_start|>user
I've had such a stressful day. It feels like everything that could go
wrong did go wrong.<|im_end|>
<|im_start|>assistant
Oh, I'm sorry to hear that. Stressful days can be really tough.
It's okay to feel overwhelmed sometimes. Would you like to talk
about what happened today, or would you prefer to shift your focus
to something more uplifting?<|im_end|>
<|im_start|>user
Where do I even start? I woke up late, missed an important meeting at work,
and then spilled coffee all over my papers. And to top it all off,
I had a disagreement with my friend.<|im_end|>
<|im_start|>assistant
Wow, that sounds like a lot to handle. I can understand why you're
feeling stressed. It's natural to feel that way. Sometimes, things
just don't go as planned, and it can be really hard to stay positive.
I'm here to listen and offer support, if you'd like.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
generated_response = simulate_conversation(dolphin, messages)Response:
I'm sorry to hear that. Conflict can be difficult, especially when it
involves someone close to us. It's understandable to feel worried about
the impact on your friendship. How about we brainstorm some ways to approach
your friend about the issue and see if there's a way to find common ground?And there you have it, Dolphin is waiting to continue the conversation with you.
There’s something soothing about Dolphin’s responses, isn’t there? I think with a little bit of work, it could feel like you’re texting a friend who really knows you and just what to say to cheer you up!
Dolphin is free to use commercially, and I can already see how this can be applied to giving personal advice, wellness coaching, roleplay therapy sessions, reflective listening, or motivational interviewing.
Let me leave you with a simulation for reflective listening that you can try yourself:
User: I've been job hunting for months now, and it's starting to get
really discouraging. I feel like I'm never going to find the right position.
Dolphin: ...
User: Exactly, and every time I get a rejection, it just makes me feel
like I'm not good enough.
Dolphin: ...
User: That's true. I put so much effort into each application,
and when they don't want me, it's hard not to take it personally.
Dolphin: ...
User: I know I shouldn't think that way, but it's hard not to.
I just want to find a job where I can be happy and contribute.
Dolphin: ...
User: Absolutely. I want to wake up and be excited about what I'm doing,
not just go through the motions.
Dolphin: ...A Personal Request to Our Valued Reader:
We envision a future where every individual is equipped with the knowledge and tools to harness the power of AI, driving positive change and innovation in the world.
Each article we publish, every notebook we share, and all the resources we offer are a testament to our commitment to this vision. We pour our passion, expertise, and countless hours into creating content that we believe can make a difference in your journey.
But, here’s a surprising fact: Out of the thousands who benefit from our content, only a mere 1% choose to follow us on Medium. Our dream is to see that number rise to 10%. Why? Because every follow is a vote of confidence, a sign that we’re on the right track, and an indicator of the topics and resources you’d love to see more of.
If you ever found value in our work, if you believe in a world empowered by AI, and if you’d like to be part of this exciting journey with us, please take a moment to Follow Us on Medium. It’s a small gesture, but it means the world to us and helps us tailor our content to your needs.
Thank you for being an integral part of our community. Together, let’s shape the future of AI.
If you want to know more about the base model Mistral-7B-v0.1, I recently wrote an article about it:
Conclusion
In short, Dolphin’s abilities are nothing short of impressive.
You can try to use it together with MemGPT, I believe it will make a difference, and you can compare how different models compare in similar settings.
Here’s a recent article that I wrote about it:
Let me know if you have questions in the comments.
See you somewhere in the matrix!
