Decoding LLM Parameters, Part 1: Temperature

The first article in this multi-part series explores how parameter tuning impacts creativity, precision, and diversity in LLM content generation.

Pavan Vemuri

Prince Bose

Tharakarama Reddy Yernapalli Sreenivasulu

Sep. 20, 24 · Tutorial

Likes (5)

Comment

Save

4.1K Views

LLM Parameters

Like any machine learning model, large language models have various parameters that control the variance of the generated text output. We have started a multi-part series to explain the impact of these parameters in detail. We will conclude by striking the perfect balance in content generation using all of these parameters discussed in our multi-part series.

Welcome to the first part, where we discuss the most well-known parameter, "Temperature."

Temperature

If the goal is to control the randomness of the predictions, then temperature is the one for you. Lower temperature values make the output more deterministic, while higher values will make it more creative by allowing diverse outcomes.

Let us look at temperature in action using the following code and output. To present the importance simply, we chose to use hugging face transformers and the GPT2 model in particular.

    Python
   
 

   import torch
from transformers import GPT2LMHeadModel, GPT2Tokenizer

# Load GPT-2 model and tokenizer
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model = GPT2LMHeadModel.from_pretrained("gpt2")

# Add pad token to tokenizer (GPT-2 doesn't have it by default)
tokenizer.pad_token = tokenizer.eos_token

# Function to generate response with varying temperature
def generate_with_temperature(prompt, temperature):
    inputs = tokenizer(prompt, return_tensors='pt', padding=True)

    # Set the attention_mask and pad_token_id
    outputs = model.generate(
        inputs.input_ids,
        attention_mask=inputs['attention_mask'], 
        do_sample=True,
        max_length=200,
        temperature=temperature,
        pad_token_id=tokenizer.eos_token_id  
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

#Prompt on which we get the content generated based on temperature
prompt = "What are some of the best strategies within NFL Fantasy"

# Test temperature variations
print("Temperature 0.3 (Less deterministic but coherent):\n", generate_with_temperature(prompt, temperature=0.3))
print("\nTemperature 0.5 (Balanced):\n", generate_with_temperature(prompt, temperature=0.5))
print("\nTemperature 0.9 (More creative):\n", generate_with_temperature(prompt, temperature=0.9))

  

Output:

    PowerShell
   
   python test_temperature.py
Temperature 0.3 (Less deterministic but coherent):
 What are some of the best strategies within NFL Fantasy Football?

I've seen a lot of great strategies for predicting the next NFL season. I've seen great strategies for predicting the next NFL season.

I've seen a lot of great strategies for predicting the next NFL season. I've seen great strategies for predicting the next NFL season.

I've seen a lot of great strategies for predicting the next NFL season. I've seen great strategies for predicting the next NFL season.

I've seen a lot of great strategies for predicting the next NFL season. I've seen great strategies for predicting the next NFL season.

I've seen a lot of great strategies for predicting the next NFL season. I've seen great strategies for predicting the next NFL season.

I've seen a lot of great strategies for predicting the next NFL season. I've seen great strategies for predicting the next NFL season.

I've seen a lot of great strategies for predicting the next

Temperature 0.5 (Balanced):
 What are some of the best strategies within NFL Fantasy Football?

1. Pick up the first pick and use it to draft a QB

In the past, I've mentioned that I tend to pick up the first pick in the first round. The best way to pick up the first pick is to take the first pick and then use it to draft a QB. I find that the more I draft the QB, the more I draft the QB. This is why I like to draft the first pick in the first round.

2. Draft a QB for the first time

This is an important one, but it's not the only one. Drafting a QB for the first time is a great way to start your fantasy season.

3. Draft a QB for the first time

This is the most important one. Drafting a QB for the first time is the most important one. Drafting a QB for the first time is the most important one.

Temperature 0.9 (More creative):
 What are some of the best strategies within NFL Fantasy?

If you are looking for players that will be good for you, here is an updated list of key stats, which you can find on our official website:

All players were ranked in the top 10 fantasy players. These players are all high-rated defensive backs or running backs with good play across all phases of their careers. The players above were ranked from 5-5 for total points scored.

The chart below will allow you to visualize the players in your league.

All players have 5.5 sacks, 5 sacks and 2.5 tackles for loss on the season. They have a combined 11.3 sacks with a 4.6, 1.6 and 2.1 yards per carry average, respectively.

Each player has three touchdowns. The three touchdowns are tied for the top five fantasy points with 3 points in an entire game. The three touchdowns are tied for the top ten points with 2 points

Let us understand the output:

Low Temperature (0.3): The model will focus on the most likely word choices. If precision and consistency matter to you, then give the temperature around this range. However, keep in mind that the model might get stuck repeating similar phrases, as is the case with our output here.
Medium Temperature (0.5): This temperature perfectly balances coherence and creativity. It is an excellent middle ground if you want a fair amount of variation without losing structure. As you can see in the output, a little balance has been added, but you could still see some repetition in the output.
High Temperature (0.9): This temperature blows up the LLM to be as creative as possible. As you can see, this output differs from the previous two, bringing in a lot of randomness and variance in the content.

The above example sets a fundamental understanding of temperature. Let us now look at it in a slightly more detailed way with a couple of use cases: "Creative Story Generation" and "Technical Explanation."

Let us look at that with the following code to understand how temperature impacts the above 2 use cases.

    Python
   
 

   import torch
from transformers import GPT2LMHeadModel, GPT2Tokenizer

# Load GPT-2 model and tokenizer
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model = GPT2LMHeadModel.from_pretrained("gpt2")

# Add pad token to tokenizer (GPT-2 doesn't have it by default)
tokenizer.pad_token = tokenizer.eos_token

# Function to generate response based on temperature
def generate_with_temperature(prompt, temperature, max_length=200):
    inputs = tokenizer(prompt, return_tensors='pt', padding=True)
    outputs = model.generate(
        inputs.input_ids,
        attention_mask=inputs['attention_mask'],
        do_sample=True,
        max_length=max_length,
        temperature=temperature,  # Only focusing on temperature
        pad_token_id=tokenizer.eos_token_id
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

### USE CASE 1: CREATIVE STORY GENERATION ###

def creative_story_generation():
    prompt = "Once upon a time, in a distant galaxy, there was a spaceship called Voyager."

    # Negative Impact: Low temperature for creative writing (too deterministic, repetitive)
    print("\n=== Creative Story with Low Temperature (0.2) - Negative Impact: ===")
    low_temp_story = generate_with_temperature(prompt, temperature=0.2)
    print(low_temp_story)

    # Perfect Impact: High temperature for creative writing (more creative and varied)
    print("\n=== Creative Story with High Temperature (0.9) - Perfect Impact: ===")
    high_temp_story = generate_with_temperature(prompt, temperature=0.9)
    print(high_temp_story)

### USE CASE 2: TECHNICAL EXPLANATION ###

def technical_explanation():
    prompt = "Explain how blockchain works in simple terms."

    # Negative Impact: High temperature for technical writing (too creative, inaccurate)
    print("\n=== Technical Explanation with High Temperature (0.9) - Negative Impact: ===")
    high_temp_explanation = generate_with_temperature(prompt, temperature=0.9)
    print(high_temp_explanation)

    # Perfect Impact: Optimal temperature for technical writing (accurate and focused)
    print("\n=== Technical Explanation with Adjusted Temperature (0.7) - Perfect Impact: ===")
    perfect_temp_explanation = generate_with_temperature(prompt, temperature=0.7)
    print(perfect_temp_explanation)

# Run both use cases
creative_story_generation()
technical_explanation()

  

Output:

    PowerShell
   
   python temperature_impact.py

=== Creative Story with Low Temperature (0.2) - Negative Impact: ===
Once upon a time, in a distant galaxy, there was a spaceship called Voyager. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been brought back from the dead by the gods. It was a spaceship that had been

=== Creative Story with High Temperature (0.9) - Perfect Impact: ===
Once upon a time, in a distant galaxy, there was a spaceship called Voyager. The ship seemed to have been flying in space as well, like the spaceship in the movie "The Voyage Home". The Captain of the Voyager was Captain Jean-Luc Picard.

In the Star Trek movies, this is true. But in the movie, on Voyager, our hero is not Jean-Luc Picard. Jean-Luc, the villain, has no desire to lead us to vengeance against the dying star.

But what about Star Trek VI: The Undiscovered Country…

In a scene that's been in development for years (one you'll almost certainly see in an upcoming Star Trek film), in the middle of the movie (one you won't see until later in the film), we see that Picard is no longer in the Star Trek universe as is the story, to be played by the same actor who played Lieutenant Dax (who was in the movie), but Picard himself.

=== Technical Explanation with High Temperature (0.9) - Negative Impact: ===
Explain how blockchain works in simple terms.

Blockchain can be used to determine if the system is trustworthy and to prevent fraud, even if the system is used in a completely different manner. Blockchain can also be used to help determine how the system is run and to ensure that its operation is efficient.

This way all your trust in the system can be verified by your actions, and you can have full control over it. When you are not trusting a computer, it can be easy to get a hold of a server and then just change the software, allowing you to control and monitor transactions with the help of the blockchain. If your business uses distributed storage then it is easy to have more control over your activities.

What do I need to understand about blockchain?

To understand how blockchain works and how you can use it properly, you must first understand how blockchain works.

Bitcoins are digital tokens, created at the start of each generation that are used to

=== Technical Explanation with Adjusted Temperature (0.7) - Perfect Impact: ===
Explain how blockchain works in simple terms.

What are the key differences between Bitcoin and Ethereum?

Blockchain is a cryptographic protocol. It can be used to create any type of transaction. It is used to store data and create new entities. It is used as a system of communication in blockchain systems.

In Ethereum, the transaction is recorded, stored, and used to perform the transaction. It is a way to transfer information. The transaction is called a "blockchain."

Since the blockchain is used for many things, it is easy to understand how the technology works. The most important difference is that Ethereum uses the blockchain to create an interface to the Internet of Things. It is this interface that allows for data exchange and the creation of new entities.

Because of this, it is possible to perform the transactions on the blockchain. So, what is the difference between Bitcoin and Ethereum?

The Bitcoin and Ethereum blockchain is a distributed ledger.

Now let us break and analyze the output for creative story generation and technical explanation based on the temperature settings and how the output was impacted. Also, we will observe how a temperature setting works perfectly for one use case and does the exact opposite for another use case.

Creative Story Generation

Low Temperature (Negative Impact): As you can see, the story output is highly repetitive and lacks variety. This result is not satisfying for a creative task, and the extreme repetitiveness caused by the model's inability to introduce novel and innovative ideas makes it undesirable for storytelling.
High Temperature (Perfect Impact): As you can see from the output, the story takes interesting directions and is very creative. The output also adds multiple aspects to the story, which makes it varied, imaginative, and perfect for innovative storytelling.

Technical Explanation

High Temperature (Negative Impact): It is important to remember that maintaining factual accuracy is very important for a use case such as a technical explanation. High temperature leads to much randomness and less probable words being introduced into the generated content, making it unsatisfactory for technical writing. The same can also be inferred from the output above that it is too vague and includes irrelevant ideas.
Adjusted Temperature (Perfect Impact): We have adjusted the temperature to a setting that strikes a perfect balance for generating technical content. As you can see, the output is much more sorted right now. At this temperature setting, the model avoids repetitiveness like it does at lower temperatures and does not lose coherence like in higher temperatures.

Conclusion

You have seen all the ways in which temperature can affect content generation and which temperature setting is perfect for which use case. Also, note that adjusting the temperature is not the be-all and end-all of content generation; you will have to tweak other parameters as well. We will look at all of that in the upcoming articles in the series.

AI Machine learning Use case

Opinions expressed by DZone contributors are their own.

Related

Trending