Downloads · 30 days
14
48% of all-time downloads
080-ai_-_flintlock_3B_v0.1-4bits
RichardErkhov/080-ai_-_flintlock_3B_v0.1-4bits
080-ai_-_flintlock_3B_v0.1-4bits 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
29
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.
flintlock_3B_v0.1 - bnb 4bits
- Model creator: https://huggingface.co/080-ai/
- Original model: https://huggingface.co/080-ai/flintlock_3B_v0.1/
Original model description:
license: apache-2.0 datasets:
- ambrosfitz/ps_data_v2.2
Model
A fine-tuned openllama 3B model, using primary sources from US History to provide a deeper understanding of the historical context.
Run history:
train/epoch ▁▁▂▂▂▃▃▄▄▄▅▅▅▆▆▇▇▇███<br> train/global_step ▁▁▂▂▂▃▃▄▄▄▅▅▅▆▆▇▇▇███<br> train/grad_norm ██▄▅▄▅▃▂▂▄▂▂▂▂▁▁▁▁▁▁<br> train/learning_rate ▂▂▃▄▅▅▆▇▇█▇▇▆▅▅▄▃▂▂▁<br> train/loss ▇█▇▆▅▅▄▄▃▃▂▂▂▁▂▁▁▁▁▁<br> train/total_flos ▁<br> train/train_loss ▁<br> train/train_runtime ▁<br> train/train_samples_per_second ▁<br> train/train_steps_per_second ▁<br>
Run summary:
train/epoch 2.0<br> train/global_step 20<br> train/grad_norm 0.13779<br> train/learning_rate 0.0<br> train/loss 1.1365<br> train/total_flos 4.579249185376512e+16<br> train/train_loss 1.29891<br> train/train_runtime 1552.5749<br> train/train_samples_per_second 1.649<br> train/train_steps_per_second 0.013<br>
- Type
- llama
- Created
- Mar 14, 2025
- Updated
- Mar 14, 2025