Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -7,8 +7,11 @@ import transformers
|
|
7 |
|
8 |
# model_from_hugging_face = transformers.pipeline("text-generation", model="TheBloke/Llama-2-7B-Chat-GGML")
|
9 |
# Load model directly
|
10 |
-
from
|
11 |
-
|
|
|
|
|
|
|
12 |
# # from langchain.llms import CTransformers
|
13 |
# from langchain_community.llms import CTransformers
|
14 |
|
@@ -27,10 +30,7 @@ def getLLMResponse(form_input,email_sender,email_recipient,email_style):
|
|
27 |
|
28 |
#C Transformers is the Python library that provides bindings for transformer models implemented in C/C++ using the GGML library
|
29 |
|
30 |
-
llm =
|
31 |
-
model_type='llama',
|
32 |
-
config={'max_new_tokens': 256,
|
33 |
-
'temperature': 0.01})
|
34 |
|
35 |
|
36 |
#Template for building the PROMPT
|
|
|
7 |
|
8 |
# model_from_hugging_face = transformers.pipeline("text-generation", model="TheBloke/Llama-2-7B-Chat-GGML")
|
9 |
# Load model directly
|
10 |
+
# with ctransformers, you can load from Hugging Face Hub directly and specify a model file (.bin or .gguf files) using:
|
11 |
+
|
12 |
+
from ctransformers import AutoModelForCausalLM
|
13 |
+
|
14 |
+
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q8_0.bin")
|
15 |
# # from langchain.llms import CTransformers
|
16 |
# from langchain_community.llms import CTransformers
|
17 |
|
|
|
30 |
|
31 |
#C Transformers is the Python library that provides bindings for transformer models implemented in C/C++ using the GGML library
|
32 |
|
33 |
+
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q8_0.bin")
|
|
|
|
|
|
|
34 |
|
35 |
|
36 |
#Template for building the PROMPT
|