RAGchat

Build error

moriire commited on Apr 29, 2024

Commit

6fb4c8d

verified ·

1 Parent(s): 5e9f4b2

Update app/llm.py

Files changed (1) hide show

app/llm.py CHANGED Viewed

@@ -31,7 +31,7 @@ class ChatModel(BaseModel):
 llm_chat = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
-    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat"),
     verbose=False,
      n_ctx=512,
      n_gpu_layers=0,
@@ -40,7 +40,7 @@ llm_chat = llama_cpp.Llama.from_pretrained(
 llm_generate = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
-    #tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-adapter-merged_16bit"),
     verbose=False,
      n_ctx=4096,
      n_gpu_layers=0,

 llm_chat = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-adapter-merged_16bit"),
     verbose=False,
      n_ctx=512,
      n_gpu_layers=0,
 llm_generate = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-adapter-merged_16bit"),
     verbose=False,
      n_ctx=4096,
      n_gpu_layers=0,