hotfix: add bytes back to llm

tinygrad/llm/cli.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 import sys, argparse, codecs, typing, re, unicodedata, json, uuid, time, pathlib
 from tinygrad import nn
+from tinygrad.uop.ops import UOp, Ops
 from tinygrad.helpers import partition, DEBUG, Timing, GlobalCounters, stderr_log, colored, Context, fetch
 from tinygrad.viz.serve import TCPServerWithReuse, HTTPRequestHandler
 from tinygrad.llm.model import Transformer
@@ -192,7 +193,8 @@ def main():
   # load the model
   model, kv = Transformer.from_gguf(fetch(models.get(args.model, args.model)), args.max_context)
   model_name = kv.get('general.name') or kv.get('general.basename') or args.model
-  print(f"using model \"{model_name}\" with {sum(x.numel() for x in nn.state.get_parameters(model)):,} params")
+  file_sizes = [y.nbytes() for y in UOp.sink(*[x.uop for x in nn.state.get_parameters(model)]).toposort() if y.op is Ops.BUFFER]
+  print(f"using model \"{model_name}\" with {sum(file_sizes):,} bytes and {sum(x.numel() for x in nn.state.get_parameters(model)):,} params")
 
   # get tokenizer
   tok = SimpleTokenizer.from_gguf_kv(kv)