Downloads · 30 days
155
0% of all-time downloads
acrastt/Marx-3B-V2
Marx-3B-V2 is a text generation model from acrastt. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
<a href="https://www.buymeacoffee.com/acrastt" target="blank"<img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" </a
Downloads · 30 days
155
0% of all-time downloads
All-time downloads
58K
Public
Parameters
3.4B
19.3 GB on disk
Likes
24
Public
Click a slice to open those files.
.bin6.9 GB · 50%
How the weights are stored.
F163.4B · 100%
From the Hugging Face model README
<a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
This is OpenLLaMA 3B V2 finetuned on EverythingLM Data V2(ShareGPT format) for 2 epochs.
Prompt template:
### HUMAN:
{prompt}
### RESPONSE:
<leave a newline for the model to answer>
q4_1 GGML quant available here.</br> q4_1 GGUF quant available here.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 42.08 |
| AI2 Reasoning Challenge (25-Shot) | 44.03 |
| HellaSwag (10-Shot) | 72.92 |
| MMLU (5-Shot) | 27.84 |
| TruthfulQA (0-shot) | 39.92 |
| Winogrande (5-shot) | 66.54 |
| GSM8k (5-shot) | 1.21 |