google-deepmind/gemma-7b 🔢📝 → 📝

▶️ 7.8K runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub ⚖️ License
code-generation question-answering text-generation

About

7B base version of Google’s Gemma model

Example Output

Prompt:

"Here is Machine Learning poem:"

Output

Machine learning,
A powerful tool,
But also a burden,
For it can’t be controlled.

It’s a double-edged sword,
A blessing and a curse,
A tool for good,
Or a tool for worse.

It can help us solve,
Complex problems with ease,
But it can also cause,
Damage and distress.

It’s a technology,
That’s changing the world,
But we must be careful,
Not to be misled by its charm.

We must consider,
The risks and the rewards,
And use it responsibly,
For the good of all.

So let’s embrace,
The power of machine learning,
And use it wisely,
For a better tomorrow.

If you like this poem, you may also like the following articles:

Performance Metrics

12.44s Prediction Time
12.47s Total Time
All Input Parameters
{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Here is Machine Learning poem:",
  "temperature": 0.7,
  "max_new_tokens": 256,
  "min_new_tokens": -1,
  "repetition_penalty": 1
}
Input Parameters
top_k Type: integerDefault: 50
When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
top_p Type: numberDefault: 0.95Range: 0 - 1
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt Type: stringDefault: Write me a poem about Machine Learning.
Prompt to send to the model.
temperature Type: numberDefault: 0.7Range: 0.01 - 5
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
max_new_tokens Type: integerDefault: 256Range: 1 - ∞
Maximum number of tokens to generate. A word is generally 2-3 tokens
min_new_tokens Type: integerDefault: -1Range: -1 - ∞
Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.
repetition_penalty Type: numberDefault: 1Range: 0 - ∞
A parameter that controls how repetitive text can be. Lower means more repetitive, while higher means less repetitive. Set to 1.0 to disable.
Output Schema

Output

Type: arrayItems Type: string

Version Details
Version ID
2ca65f463a2c0cfef4dbc4ba70d227ed96455ef6020c1f6983b2a4c4f3ecb4ec
Version Created
February 21, 2024
Run on Replicate →