Merge 8cfa0451f4 into a445144d39

nanochat/gpt.py

@@ -238,11 +238,6 @@ class GPT(nn.Module):
         for i in range(n_layer):
             self.x0_lambdas.data[i] = 0.20 - (0.15 * i / max(n_layer - 1, 1))
 
-        # Smear/backout scalars and smear gate must be explicitly initialized 
-        torch.nn.init.zeros_(self.smear_lambda)
-        torch.nn.init.constant_(self.backout_lambda, 0.2)
-        torch.nn.init.uniform_(self.smear_gate.weight, 0.0, 0.02)
-
         # Value embeddings (init like c_v: uniform with same std)
         for ve in self.value_embeds.values():
             torch.nn.init.uniform_(ve.weight, -s, s)

pyproject.toml

@@ -54,7 +54,6 @@ explicit = true
 
 [project.optional-dependencies]
 cpu = [
-    "setuptools>=65.0.0",
     "torch==2.9.1",
 ]
 gpu = [

uv.lock

@@ -1507,7 +1507,6 @@ dependencies = [
 
 [package.optional-dependencies]
 cpu = [
-    { name = "setuptools" },
     { name = "torch", version = "2.9.1", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(sys_platform == 'darwin' and extra == 'extra-8-nanochat-cpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
     { name = "torch", version = "2.9.1+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(sys_platform != 'darwin' and extra == 'extra-8-nanochat-cpu') or (extra == 'extra-8-nanochat-cpu' and extra == 'extra-8-nanochat-gpu')" },
 ]
@@ -1531,7 +1530,6 @@ requires-dist = [
     { name = "kernels", specifier = ">=0.11.7" },
     { name = "psutil", specifier = ">=7.1.0" },
     { name = "rustbpe", specifier = ">=0.1.0" },
-    { name = "setuptools", marker = "extra == 'cpu'", specifier = ">=65.0.0" },
     { name = "tiktoken", specifier = ">=0.11.0" },
     { name = "tokenizers", specifier = ">=0.22.0" },
     { name = "torch", specifier = "==2.9.1" },