Upload README.md with huggingface_hub

README.md

@@ -41,6 +41,7 @@ Chat-Node is a conversational variant of [Pacific-Prime 1.5B](https://huggingfac
 | Base Model | Pacific-Prime 1.5B v0.13.0 |
 | Parameters | ~1.52B |
 | Fine-tuning | SFT (Supervised Fine-Tuning) |
+| Base Checkpoint | pacific-prime-python epoch 450 |
 | Dataset | [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned) (20K samples) |
 | Current Epoch | 350 |
 | Precision | F32 |
@@ -53,7 +54,7 @@ Chat-Node is a conversational variant of [Pacific-Prime 1.5B](https://huggingfac
 |-----------|-------|
 | Learning Rate | 2e-5 |
 | Batch Size | 4 |
-| Gradient Accumulation | 16 (effective batch: 64) |
+| Gradient Accumulation | 8 (effective batch: 32) |
 | Weight Decay | 0.01 |
 | Warmup Ratio | 3% |
 | Gradient Checkpointing | Enabled |
@@ -164,6 +165,7 @@ print(tokenizer.decode(output[0].tolist()))
 - [Base Model - Pacific-Prime 1.5B](https://huggingface.co/Pacific-Prime/pacific-prime)
 - [GitHub - complexity-deep](https://github.com/Complexity-ML/complexity-deep)
 - [PyPI - complexity-deep](https://pypi.org/project/complexity-deep/)
+- [GitHub - mu-inference](https://github.com/Complexity-ML/mu-inference)
 
 ---