upgrading all other files to be able to use cpu/mps as well as cuda. various minor other changes ,e.g. changing max_iterations to num_iterations in sft script for consistency in naming

scripts/chat_cli.py

@@ -6,7 +6,8 @@ python -m scripts.chat_cli -i mid
 """
 import argparse
 import torch
-from nanochat.common import compute_init
+from nanochat.common import compute_init, autodetect_device_type
+from contextlib import nullcontext
 from nanochat.engine import Engine
 from nanochat.checkpoint_manager import load_model
 
@@ -17,11 +18,16 @@ parser.add_argument('-s', '--step', type=int, default=None, help='Step to load')
 parser.add_argument('-p', '--prompt', type=str, default='', help='Prompt the model, get a single response back')
 parser.add_argument('-t', '--temperature', type=float, default=0.6, help='Temperature for generation')
 parser.add_argument('-k', '--top-k', type=int, default=50, help='Top-k sampling parameter')
+parser.add_argument('--device-type', type=str, default='', choices=['cuda', 'cpu', 'mps'], help='Device type for evaluation: cuda|cpu|mps. empty => autodetect')
+parser.add_argument('-d', '--dtype', type=str, default='bfloat16', choices=['float32', 'bfloat16'])
 args = parser.parse_args()
 
 # Init the model and tokenizer
-ddp, ddp_rank, ddp_local_rank, ddp_world_size, device = compute_init()
-autocast_ctx = torch.amp.autocast(device_type="cuda", dtype=torch.bfloat16)
+
+device_type = autodetect_device_type() if args.device_type == "" else args.device_type
+ddp, ddp_rank, ddp_local_rank, ddp_world_size, device = compute_init(device_type)
+ptdtype = torch.float32 if args.dtype == 'float32' else torch.bfloat16
+autocast_ctx = torch.amp.autocast(device_type=device_type, dtype=ptdtype) if device_type == "cuda" else nullcontext()
 model, tokenizer, meta = load_model(args.source, device, phase="eval", model_tag=args.model_tag, step=args.step)
 
 # Special tokens for the chat state machine