File size: 1,477 Bytes
f774aea ca26e2b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
---
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.
|