---
license: apache-2.0
datasets:
- VMware/open-instruct
base_model: BEE-spoke-data/smol_llama-220M-GQA
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
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.  \n   \n### Instruction:  \n  \nWrite an ode to Chipotle burritos.\
    \ \n  \n### Response:  \n"
  example_title: burritos
model-index:
- name: smol_llama-220M-open_instruct
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 25.0
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 29.71
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 26.11
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 44.06
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 50.28
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 0.0
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
      name: Open LLM Leaderboard
---


# 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.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/MdOB7TD5UosPGZvdZWG0I.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: 1.04
    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](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BEE-spoke-data__smol_llama-220M-open_instruct)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |29.19|
|AI2 Reasoning Challenge (25-Shot)|25.00|
|HellaSwag (10-Shot)              |29.71|
|MMLU (5-Shot)                    |26.11|
|TruthfulQA (0-shot)              |44.06|
|Winogrande (5-shot)              |50.28|
|GSM8k (5-shot)                   | 0.00|