fix problem

This commit is contained in:
csunny 2023-04-30 23:59:11 +08:00
parent 7861fc28ce
commit ed9b62d9d3
2 changed files with 2 additions and 2 deletions

View File

@ -19,7 +19,7 @@ llm_model_config = {
LLM_MODEL = "vicuna-13b"
LIMIT_MODEL_CONCURRENCY = 5
MAX_POSITION_EMBEDDINGS = 2048
vicuna_model_server = "http://192.168.31.114:21002"
vicuna_model_server = "http://192.168.31.114:8000"
# Load model config

View File

@ -157,7 +157,7 @@ def http_bot(state, temperature, max_new_tokens, request: gr.Request):
try:
# Stream output
response = requests.post(urljoin(vicuna_model_server, "worker_generate_stream"),
response = requests.post(urljoin(vicuna_model_server, "generate_stream"),
headers=headers, json=payload, stream=True, timeout=20)
for chunk in response.iter_lines(decode_unicode=False, delimiter=b"\0"):
if chunk: