smol_llama-220M-open_instruct

BEE-spoke-data/smol_llama-220M-open_instruct

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.  

### Response:

This was not trained using a separate 'inputs' field (as VMware/open-instruct doesn't use one).

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.

Note that the inference API parameters used here are an initial educated guess, and may be updated over time:

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: 1.04
    no_repeat_ngram_size: 6
    epsilon_cutoff: 0.0006

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

This was trained on VMware/open-instruct so do whatever you want, provided it falls under the base apache-2.0 license :)

---

Open LLM Leaderboard Evaluation Results

Detailed results can be found here