stability-ai/stablelm-tuned-alpha-7b

7 billion parameter version of Stability AI's language model

Capabilities

Max TokensTop-P

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`max_new_tokens`	integer	Maximum number of tokens to generate. A word is generally 2-3 tokens	`100`	min: 1
`prompt`	string	Input Prompt.	`"What's your mood today?"`	—
`repetition_penalty`	number	Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.	`1.2`	min: 0.01, max: 5
`temperature`	number	Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.	`0.75`	min: 0.01, max: 5
`top_p`	number	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	`1`	min: 0.01, max: 1

max_new_tokensinteger

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 100min: 1

promptstring

Input Prompt.

Default: "What's your mood today?"

repetition_penaltynumber

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Default: 1.2min: 0.01, max: 5

temperaturenumber

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.75min: 0.01, max: 5

top_pnumber

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

Default: 1min: 0.01, max: 1

Version: 943c4afb4d02Updated: 7/25/2026140.6K runs