Update app/llm.py
Browse files- app/llm.py +1 -1
app/llm.py
CHANGED
@@ -31,7 +31,7 @@ class ChatModel(BaseModel):
|
|
31 |
mirostat_eta: float=1.1
|
32 |
llm_chat = llama_cpp.Llama.from_pretrained(
|
33 |
repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
|
34 |
-
filename="*
|
35 |
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat-GGUF"),
|
36 |
verbose=False,
|
37 |
n_ctx=256,
|
|
|
31 |
mirostat_eta: float=1.1
|
32 |
llm_chat = llama_cpp.Llama.from_pretrained(
|
33 |
repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
|
34 |
+
filename="*q4_0.gguf",
|
35 |
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat-GGUF"),
|
36 |
verbose=False,
|
37 |
n_ctx=256,
|