Trained Models 🏋️
Collection
They may be small, but they're training like giants!
•
8 items
•
Updated
•
16
A Llama Chat Model of 101M Parameters
- Base model: BEE-spoke-data/smol_llama-101M-GQA
- Datasets:
- Availability in other ML formats:
Recommended Prompt Format
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
Recommended Inference Parameters
penalty_alpha: 0.5
top_k: 4
repetition_penalty: 1.105
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 28.73 |
| AI2 Reasoning Challenge (25-Shot) | 22.87 |
| HellaSwag (10-Shot) | 28.69 |
| MMLU (5-Shot) | 24.93 |
| TruthfulQA (0-shot) | 45.76 |
| Winogrande (5-shot) | 50.04 |
| GSM8k (5-shot) | 0.08 |
- Downloads last month
- 140
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Finetuned from
Datasets used to train Felladrin/Smol-Llama-101M-Chat-v1
Spaces using Felladrin/Smol-Llama-101M-Chat-v1 2
Collection including Felladrin/Smol-Llama-101M-Chat-v1
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard22.870
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard28.690
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard24.930
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard45.760
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard50.040
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.080