Downloads · 30 days
3
10% of all-time downloads
harborwater_-_open-llama-3b-everything-v2-4bits
RichardErkhov/harborwater_-_open-llama-3b-everything-v2-4bits
harborwater_-_open-llama-3b-everything-v2-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
30
Public
Parameters
3.5B
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 100%
Parameter types
How the weights are stored.
U83.2B · 93%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
open-llama-3b-everything-v2 - bnb 4bits
- Model creator: https://huggingface.co/harborwater/
- Original model: https://huggingface.co/harborwater/open-llama-3b-everything-v2/
Original model description:
license: apache-2.0 datasets:
- totally-not-an-llm/EverythingLM-data-V2-sharegpt language:
- en library_name: transformers
Trained on 3 epochs of the totally-not-an-llm/EverythingLM-data-V2-sharegpt dataset.
### HUMAN:
{prompt}
### RESPONSE:
<leave a newline for the model to answer>
note: Changed a few of the finetuning parameters this time around. I have no idea if its any good but Feel free to give it a try!
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 36.29 |
| ARC (25-shot) | 42.83 |
| HellaSwag (10-shot) | 73.28 |
| MMLU (5-shot) | 26.87 |
| TruthfulQA (0-shot) | 37.26 |
| Winogrande (5-shot) | 66.61 |
| GSM8K (5-shot) | 1.59 |
| DROP (3-shot) | 5.61 |
- Type
- llama
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024