Spaces:
Sleeping
Sleeping
File size: 2,294 Bytes
489cc5d 5186d1b 489cc5d 5186d1b 29519fd 5186d1b 489cc5d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
from langchain.prompts import PromptTemplate
from langchain.llms import CTransformers
from langchain.chains import LLMChain
from langchain.chains import SequentialChain
config = {'max_new_tokens': 256, 'temperature': 0.1}
# Create function for app
def GetLLMResponse(selected_topic_level,
selected_topic,
num_quizzes):
# Calling llama model
# llm = CTransformers(model="D:\Code Workspace\DL Model\llama-2-7b-chat.ggmlv3.q8_0.bin",
# model_type = 'llama',
# config = config)
llm = CTransformers(model='TheBloke/Llama-2-7B-Chat-GGML',
model_file = 'llama-2-7b-chat.ggmlv3.q8_0.bin',
model_type = 'llama',
config = config)
## Create LLM Chaining
questions_template = "Generate a {selected_topic_level} math quiz on the topic of {selected_topic}. Include {num_quizzes} questions without providing answers."
questions_prompt = PromptTemplate(input_variables=["selected_topic_level", "selected_topic", "num_quizzes"],
template=questions_template)
questions_chain = LLMChain(llm= llm,
prompt = questions_prompt,
output_key = "questions")
answer_template = "From this Question:\n {questions}\n\n gave me answer to each one of them"
answer_prompt = PromptTemplate(input_variables = ["questions"],
template = answer_template)
answer_chain = LLMChain(llm = llm,
prompt = answer_prompt,
output_key = "answer")
## Create Sequential Chaining
seq_chain = SequentialChain(chains = [questions_chain, answer_chain],
input_variables = ['selected_topic_level', 'selected_topic', 'num_quizzes'],
output_variables = ['questions', 'answer'])
response = seq_chain({'selected_topic_level': selected_topic_level,
'selected_topic': selected_topic,
'num_quizzes' : num_quizzes})
## Generate the response from the llama 2 model
print(response)
return response |