|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- teknium/openhermes |
|
inference: |
|
parameters: |
|
do_sample: true |
|
renormalize_logits: true |
|
temperature: 0.25 |
|
top_p: 0.95 |
|
top_k: 50 |
|
min_new_tokens: 2 |
|
max_new_tokens: 96 |
|
repetition_penalty: 1.1 |
|
no_repeat_ngram_size: 6 |
|
epsilon_cutoff: 0.0006 |
|
widget: |
|
- text: > |
|
Below is an instruction that describes a task, paired with an input that |
|
provides further context. Write a response that appropriately completes |
|
the request. |
|
|
|
### Instruction: |
|
|
|
Write an ode to Chipotle burritos. |
|
|
|
### Response: |
|
example_title: burritos |
|
--- |
|
|
|
|
|
# BEE-spoke-data/smol_llama-220M-openhermes |
|
|
|
|
|
prompt format is alpaca |
|
|
|
|
|
``` |
|
Below is an instruction that describes a task, paired with an input that |
|
provides further context. Write a response that appropriately completes |
|
the request. |
|
|
|
### Instruction: |
|
|
|
How can I increase my meme production/output? Currently, I only create them in ancient babylonian which is time consuming. |
|
|
|
### Inputs: |
|
|
|
### Response: |
|
``` |
|
|
|
It was trained on inputs so if you have inputs (like some text to ask a question about) then include it under `### Inputs:` |
|
|
|
|
|
## Example |
|
|
|
Output on the text above ^. The inference API is set to sample with low temp so you should see (_at least slightly_) different inputs each time. |
|
|
|
|
|
 |
|
|
