Petro
commited on
Commit
•
299f41e
1
Parent(s):
036f518
model
Browse files- main.py +0 -1
- requirements.txt +2 -1
main.py
CHANGED
|
@@ -9,7 +9,6 @@ model_path = "zephyr-7b-beta.Q4_K_S.gguf"
|
|
| 9 |
llm = Llama(model_path=model_path, n_ctx=512, max_answer_len=100) # Set chat_format according to the model you are using
|
| 10 |
|
| 11 |
|
| 12 |
-
|
| 13 |
class validation(BaseModel):
|
| 14 |
prompt: str
|
| 15 |
|
|
|
|
| 9 |
llm = Llama(model_path=model_path, n_ctx=512, max_answer_len=100) # Set chat_format according to the model you are using
|
| 10 |
|
| 11 |
|
|
|
|
| 12 |
class validation(BaseModel):
|
| 13 |
prompt: str
|
| 14 |
|
requirements.txt
CHANGED
|
@@ -5,4 +5,5 @@ uvicorn
|
|
| 5 |
requests
|
| 6 |
python-dotenv
|
| 7 |
ctransformers
|
| 8 |
-
torch
|
|
|
|
|
|
| 5 |
requests
|
| 6 |
python-dotenv
|
| 7 |
ctransformers
|
| 8 |
+
torch
|
| 9 |
+
llama-cpp-python==0.2.53
|