File size: 1,390 Bytes
e16fcc6 6ba5d19 e16fcc6 6ba5d19 e16fcc6 |
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 |
from huggingface_hub import hf_hub_download
model_name_or_path = "hlhr202/llama-7B-ggml-int4"
model_basename = "ggml-model-q4_0.bin" # the model is in bin format
model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool.
n_batch = 256
import paperscraper
from paperqa import Docs
from langchain.llms import LlamaCpp
from langchain import PromptTemplate, LLMChain
from langchain.callbacks.manager import CallbackManager
from langchain.embeddings import LlamaCppEmbeddings
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
# Make sure the model path is correct for your system!
llm = LlamaCpp(
model_path=model_path, callbacks=[StreamingStdOutCallbackHandler()]
)
embeddings = LlamaCppEmbeddings(model_path=model_path )
docs = Docs(llm=llm, embeddings=embeddings)
keyword_search = 'bispecific antibody manufacture'
papers = paperscraper.search_papers(keyword_search, limit=2)
for path,data in papers.items():
try:
docs.add(path,chunk_chars=500)
except ValueError as e:
print('Could not read', path, e)
answer = docs.query("What manufacturing challenges are unique to bispecific antibodies?")
print(answer)
def re(r):
print(answer)
return r
gr.Interface(fn=re,inputs=gr.Textbox(),outputs=gr.Textbox).launch() |