tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-04-03 22:25:27 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge 20c385e8f7 into c7ba252142

Browse Source
This commit is contained in:
Pramod Dhungana 2026-03-01 08:52:24 -05:00 committed by GitHub
commit 2943471f87
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/chat_web.py
View File

@ -62,7 +62,7 @@ MAX_MAX_TOKENS = 4096
parser = argparse.ArgumentParser(description='NanoChat Web Server')
parser.add_argument('-n', '--num-gpus', type=int, default=1, help='Number of GPUs to use (default: 1)')
parser.add_argument('-i', '--source', type=str, default="sft", help="Source of the model: sft|rl")
parser.add_argument('-i', '--source', type=str, default="sft", choices=["sft", "rl"], help="Source of the model: sft|rl")
parser.add_argument('-t', '--temperature', type=float, default=0.8, help='Default temperature for generation')
parser.add_argument('-k', '--top-k', type=int, default=50, help='Default top-k sampling parameter')
parser.add_argument('-m', '--max-tokens', type=int, default=512, help='Default max tokens for generation')
@ -360,7 +360,7 @@ async def chat_completions(request: ChatRequest):
top_k=request.top_k
):
# Accumulate response for logging
chunk_data = json.loads(chunk.replace("data: ", "").strip())
chunk_data = json.loads(chunk.removeprefix("data: ").strip())
if "token" in chunk_data:
response_tokens.append(chunk_data["token"])
yield chunk