adirik/mamba-130m 🔢📝 → 📝

▶️ 146 runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
mamba state-space-model text-generation

About

Base version of Mamba 130M, a 130 million parameter state space language model

Example Output

Prompt:

"How are you doing today?"

Output

I'm just getting back from a trip to the beach. I've been working on my new book, and it's going really well! It was great seeing you guys again last week at our first meeting with your team in New York City (we're still in NYC). We had such an amazing time there that we decided not only did we want more of your work but also wanted some extra time for us as part-time writers so this is what happened:
We were able get together

Performance Metrics

5.45s Prediction Time
89.02s Total Time
All Input Parameters 
{
  "top_k": 1,
  "top_p": 1,
  "prompt": "How are you doing today?",
  "max_length": 100,
  "temperature": 1,
  "repetition_penalty": 1.2
}
Input Parameters
seed Type: integer
The seed for the random number generator
top_k Type: integerDefault: 1
When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens.
top_p Type: numberDefault: 1Range: 0.01 - 1
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens.
prompt (required) Type: string
Text prompt to send to the model.
max_length Type: integerDefault: 100Range: 1 - 5000
Maximum number of tokens to generate. A word is generally 2-3 tokens.
temperature Type: numberDefault: 1Range: 0.1 - 5
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
repetition_penalty Type: numberDefault: 1.2Range: 0.01 - 10
Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.
Output Schema

Output

Type: array • Items Type: string

Version Details
Version ID
d7fe29cf1ad11cbd2fc28b808a7a7b4fd1ff880c394eaef914e40b6da08934ce
Version Created
February 5, 2024
Run on Replicate →