stability-ai/stablelm-base-alpha-3b 🔢📝 → 📝

▶️ 453 runs 📅 May 2023 ⚙️ Cog 0.7.0-beta17 🔗 GitHub ⚖️ License
text-generation

About

3B parameter base version of Stability AI's language model

Example Output

Prompt:

"Simply put, the theory of relativity states that"

Output

gravity has to be a force or some sort. This could explain many phenomena in nature and is also one reason why physicists do not really want their equations describing gravitation as we know them today."
If he's right about dark matter there are decades worth left behind by existing studies - if they detect even something like those evidenced so far no signs yet link it up well enough for government measurements – which means governments can always use discretion when making ultramarginal choices involving lethal options such an stuff

Performance Metrics

3.17s Prediction Time
3.21s Total Time
All Input Parameters
{
  "top_p": 1,
  "prompt": "Simply put, the theory of relativity states that",
  "max_tokens": 100,
  "temperature": 0.75,
  "repetition_penalty": 1.2
}
Input Parameters
top_p Type: numberDefault: 1Range: 0.01 - 1
Valid if you choose top_p decoding. When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt Type: stringDefault: What's your mood today?
Input Prompt.
max_tokens Type: integerDefault: 100Range: 1 - ∞
Maximum number of tokens to generate. A word is generally 2-3 tokens
temperature Type: numberDefault: 0.75Range: 0.01 - 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 - 5
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: arrayItems Type: string

Example Execution Logs
prompt: Simply put, the theory of relativity states that
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:0 for open-end generation.
Version Details
Version ID
90202e79dbb2a8fe154c0c0394a413c79965863a860bda2a2ee220c5a840ec50
Version Created
May 2, 2023
Run on Replicate →