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.
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: 1.03
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
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 29.34 |
AI2 Reasoning Challenge (25-Shot) | 25.17 |
HellaSwag (10-Shot) | 28.98 |
MMLU (5-Shot) | 26.17 |
TruthfulQA (0-shot) | 43.08 |
Winogrande (5-shot) | 52.01 |
GSM8k (5-shot) | 0.61 |
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 4.76 |
IFEval (0-Shot) | 15.55 |
BBH (3-Shot) | 3.11 |
MATH Lvl 5 (4-Shot) | 0.00 |
GPQA (0-shot) | 2.35 |
MuSR (0-shot) | 6.22 |
MMLU-PRO (5-shot) | 1.34 |
- Downloads last month
- 1,412
Model tree for BEE-spoke-data/smol_llama-220M-openhermes
Base model
BEE-spoke-data/smol_llama-220M-GQADataset used to train BEE-spoke-data/smol_llama-220M-openhermes
Collection including BEE-spoke-data/smol_llama-220M-openhermes
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard25.170
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard28.980
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard26.170
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard43.080
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard52.010
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.610
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard15.550
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard3.110
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard2.350