The final model (R1) is now out.

More details about the experimentation at https://github.com/MehdiSkilll24/Alpha/blob/main/README.md

R1/R1_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ef1d3a0db639f7aa542794edf6b9747b651d608a42b3f56aa2a751b8b5a21c
+size 121743856

R1/experiment_config.json

@@ -0,0 +1,10 @@
+{
+    "model_type": "encoder-decoder-transformer",
+    "d_model": 256,
+    "layers": {
+        "encoder": 3,
+        "decoder": 3
+    },
+    "vocab_size": 32000,
+    "parameters": 30137600
+}