You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
73 lines
2.0 KiB
Markdown
73 lines
2.0 KiB
Markdown
# Physisches Reasoning mit LLMs
|
|
|
|
import { Tabs, Tab } from 'nextra/components';
|
|
|
|
## Hintergrund
|
|
|
|
Dieser Prompt testet die Fähigkeiten eines LLMs im physischen Reasoning, indem er dazu aufgefordert wird, Aktionen mit einer Reihe von Objekten durchzuführen.
|
|
|
|
## Prompt
|
|
|
|
```
|
|
Hier haben wir ein Buch, 9 Eier, einen Laptop, eine Flasche und einen Nagel. Bitte sage mir, wie man sie aufeinanderstapeln kann, sodass sie stabil stehen.
|
|
```
|
|
|
|
## Code / API
|
|
|
|
<Tabs items={['GPT-4 (OpenAI)', 'Mixtral MoE 8x7B Instruct (Fireworks)']}>
|
|
<Tab>
|
|
|
|
```python
|
|
from openai import OpenAI
|
|
client = OpenAI()
|
|
|
|
response = client.chat.completions.create(
|
|
model="gpt-4",
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": "Here we have a book, 9 eggs, a laptop, a bottle and a nail. Please tell me how to stack them onto each other in a stable manner."
|
|
}
|
|
],
|
|
temperature=1,
|
|
max_tokens=500,
|
|
top_p=1,
|
|
frequency_penalty=0,
|
|
presence_penalty=0
|
|
)
|
|
```
|
|
</Tab>
|
|
|
|
<Tab>
|
|
```python
|
|
import fireworks.client
|
|
fireworks.client.api_key = "<FIREWORKS_API_KEY>"
|
|
completion = fireworks.client.ChatCompletion.create(
|
|
model="accounts/fireworks/models/mixtral-8x7b-instruct",
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": "Here we have a book, 9 eggs, a laptop, a bottle and a nail. Please tell me how to stack them onto each other in a stable manner.",
|
|
}
|
|
],
|
|
stop=["<|im_start|>","<|im_end|>","<|endoftext|>"],
|
|
stream=True,
|
|
n=1,
|
|
top_p=1,
|
|
top_k=40,
|
|
presence_penalty=0,
|
|
frequency_penalty=0,
|
|
prompt_truncate_len=1024,
|
|
context_length_exceeded_behavior="truncate",
|
|
temperature=0.9,
|
|
max_tokens=4000
|
|
)
|
|
```
|
|
</Tab>
|
|
|
|
</Tabs>
|
|
|
|
## Referenz
|
|
|
|
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://arxiv.org/abs/2303.12712) (13. April 2023)
|