fix : server model download
This commit is contained in:
@@ -13,12 +13,12 @@ class LlamacppLLM(GeneratorLLM):
|
|||||||
|
|
||||||
def generate(self, history):
|
def generate(self, history):
|
||||||
if self.llm is None:
|
if self.llm is None:
|
||||||
|
self.logger.info(f"Loading {self.model}...")
|
||||||
self.llm = Llama.from_pretrained(
|
self.llm = Llama.from_pretrained(
|
||||||
repo_id=self.model,
|
repo_id=self.model,
|
||||||
filename="*Q8_0.gguf",
|
filename="*Q8_0.gguf",
|
||||||
verbose=True
|
verbose=True
|
||||||
)
|
)
|
||||||
return
|
|
||||||
self.logger.info(f"Using {self.model} for generation with Llama.cpp")
|
self.logger.info(f"Using {self.model} for generation with Llama.cpp")
|
||||||
try:
|
try:
|
||||||
with self.state.lock:
|
with self.state.lock:
|
||||||
|
|||||||
Reference in New Issue
Block a user