Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+# Modded NanoGPT Model
+
+This is a GPT-2 style model trained with modifications from modded-nanogpt.
+
+## Model Config
+
+- Layers: 2
+- Heads: 4
+- Embedding dimension: 64
+- Vocab size: 50304
+- Squared MLP: False
+- Bilinear: False
+- Gated: False
+- Expansion factor: 4
+
+## Training
+
+- Training step: 500
+
+## Usage
+
+```python
+from huggingface_hub import hf_hub_download
+import torch
+from train_gpt2 import GPT, GPTConfig
+import json
+
+# Download config
+config_path = hf_hub_download(repo_id="Elriggs/gpt2-debug-baseline", filename="config.json")
+with open(config_path) as f:
+    config_dict = json.load(f)
+
+# Remove non-GPTConfig fields
+config_dict.pop('step', None)
+
+# Create model
+config = GPTConfig(**config_dict)
+model = GPT(config)
+
+# Download and load weights
+weights_path = hf_hub_download(repo_id="Elriggs/gpt2-debug-baseline", filename="pytorch_model.bin")
+state_dict = torch.load(weights_path, map_location='cpu')
+model.load_state_dict(state_dict)
+
+model.eval()
+```

config.json

@@ -0,0 +1,12 @@
+{
+  "vocab_size": 50304,
+  "n_layer": 2,
+  "n_head": 4,
+  "n_embd": 64,
+  "squared_mlp": false,
+  "bilinear": false,
+  "expansion_factor": 4,
+  "gated": false,
+  "squared_attn": false,
+  "step": 500
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf4cb4eadfd5675bf5a2eb5af5c4e1f72cd3a0b0686506adf39a844e62c7875
+size 19717251