Spaces:
Running
Running
change model to Llama-2-13B-chat-GGUF
Browse files
app.py
CHANGED
@@ -44,7 +44,8 @@ hf_embeddings = HuggingFaceInstructEmbeddings(
|
|
44 |
db = Chroma.from_documents(texts, hf_embeddings)
|
45 |
|
46 |
st.write('loading LLM')
|
47 |
-
model_name_or_path = "TheBloke/Llama-2-13B-chat-GPTQ"
|
|
|
48 |
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
|
49 |
|
50 |
model_basename = "model"
|
|
|
44 |
db = Chroma.from_documents(texts, hf_embeddings)
|
45 |
|
46 |
st.write('loading LLM')
|
47 |
+
#model_name_or_path = "TheBloke/Llama-2-13B-chat-GPTQ"
|
48 |
+
model_name_or_path = "TheBloke/Llama-2-13B-chat-GGUF"
|
49 |
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
|
50 |
|
51 |
model_basename = "model"
|