updated
Browse files
app.py
CHANGED
@@ -18,8 +18,10 @@ from langchain_core.outputs import Generation
|
|
18 |
from typing import Any, List, Optional, Type, TypeVar, Union
|
19 |
|
20 |
## Defining few variables
|
21 |
-
MODEL_PATH = "TheBloke/Mistral-7B-Claude-Chat-GGUF"
|
22 |
-
MODEL_FILE = "mistral-7b-claude-chat.Q4_K_M.gguf"
|
|
|
|
|
23 |
MODEL_TYPE = "mistral"
|
24 |
MAX_NEW_TOKENS = 100
|
25 |
temperature = 1
|
@@ -107,7 +109,7 @@ data = data_loader.load()
|
|
107 |
data = [doc.page_content for doc in data]
|
108 |
|
109 |
splitter = CharacterTextSplitter(chunk_size=2, chunk_overlap=1)
|
110 |
-
documents = splitter.
|
111 |
|
112 |
docs_str = [doc.page_content for doc in documents]
|
113 |
sentence_emb = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
|
|
|
18 |
from typing import Any, List, Optional, Type, TypeVar, Union
|
19 |
|
20 |
## Defining few variables
|
21 |
+
# MODEL_PATH = "TheBloke/Mistral-7B-Claude-Chat-GGUF"
|
22 |
+
# MODEL_FILE = "mistral-7b-claude-chat.Q4_K_M.gguf"
|
23 |
+
MODEL_PATH = "TheBloke/zephyr-7B-beta-GGUF"
|
24 |
+
MODEL_FILE = "zephyr-7b-beta.Q4_K_M.gguf"
|
25 |
MODEL_TYPE = "mistral"
|
26 |
MAX_NEW_TOKENS = 100
|
27 |
temperature = 1
|
|
|
109 |
data = [doc.page_content for doc in data]
|
110 |
|
111 |
splitter = CharacterTextSplitter(chunk_size=2, chunk_overlap=1)
|
112 |
+
documents = splitter.split_documents(data)
|
113 |
|
114 |
docs_str = [doc.page_content for doc in documents]
|
115 |
sentence_emb = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
|