pszemraj's picture
Update README.md
356848c
|
raw
history blame
2.39 kB
---
license: apache-2.0
base_model: BEE-spoke-data/smol_llama-220M-GQA
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: 1.03
no_repeat_ngram_size: 5
epsilon_cutoff: 0.0008
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
> Please note that this is an experiment, and the model has limitations because it is smol.
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 generations each time.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/0nFP2jsBkritnryKmI8NV.png)
Note that the inference API parameters used here are an initial educated guess, and may be updated over time:
```yml
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: 1.03
no_repeat_ngram_size: 5
epsilon_cutoff: 0.0008
```
Feel free to experiment with the parameters using the model in Python and let us know if you have improved results with other params!
## Data
Note that **this checkpoint** was fine-tuned on `teknium/openhermes`, which is generated/synthetic data by an OpenAI model. This means usage of this checkpoint should follow their terms of use: https://openai.com/policies/terms-of-use
---