Duplicate from tommy24/llm

Co-authored-by: Tommy <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Llm
+emoji: 🌍
+colorFrom: red
+colorTo: red
+sdk: gradio
+sdk_version: 3.36.1
+app_file: app.py
+pinned: false
+duplicated_from: tommy24/llm
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,75 @@
+import gradio as gr
+from langchain.llms import LlamaCpp
+from langchain import PromptTemplate, LLMChain
+from langchain.llms import GPT4All
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
+
+# import requests
+
+# url = "https://huggingface.co/TheBloke/Nous-Hermes-13B-GGML/resolve/main/nous-hermes-13b.ggmlv3.q4_0.bin"
+
+# response = requests.get(url)
+
+# with open("nous-hermes-13b.ggmlv3.q4_0.bin", "wb") as f:
+#     f.write(response.content)
+
+
+print("DONE")
+
+def func(user):
+        
+    template = """
+    Your name is John and not a assistant but more like a chatbot. Respond precise not more words and act like a human. for example: user: How are you? You: I'm doing good how about you?. user: hello You: Hello how you doing?. Don't say How can I assist you today?.
+    Question: {question}
+    
+    Answer: """
+    
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+    
+    local_path = (
+        "./model.bin"
+    )
+
+    
+    # # Callbacks support token-wise streaming
+    # callbacks = [StreamingStdOutCallbackHandler()]
+    
+    # Verbose is required to pass to the callback manager
+    llm = LlamaCpp(model_path=("./model.bin"))
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    question = user
+    llm_chain.run(question)
+
+    return llm_chain.run(question)
+
+iface = gr.Interface(fn=func, inputs="text", outputs="text")
+iface.launch()
+
+# import gradio as gr
+# from langchain.llms import LlamaCpp
+# from langchain import PromptTemplate, LLMChain
+# from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
+# print("DONE")
+
+# def func(user):
+#     template = """
+#     Your name is John and not a assistant but more like a chatbot. Respond precise not more words and act like a human. for example: user: How are you? You: I'm doing good how about you?. user: hello You: Hello how you doing?. Don't say How can I assist you today?.
+#     Question: {question}
+    
+#     Answer: """
+    
+#     prompt = PromptTemplate(template=template, input_variables=["question"])
+    
+#     local_path = "./nous-hermes-13b.ggmlv3.q4_0.bin"
+    
+#     llm = LlamaCpp(model_path=local_path)
+#     llm_chain = LLMChain(prompt=prompt, llm=llm, streaming=True)  # Enable streaming mode
+#     question = user
+#     llm_chain.run(question)
+
+#     return llm_chain.run(question)
+
+# iface = gr.Interface(fn=func, inputs="text", outputs="text")
+# iface.launch()

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2fd7cca97284467de0be8f638925f40cbff4c70a2e10ba1094f83bfa24d86b
+size 3785248281

nous-hermes-13b.ggmlv3.q4_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1735b93e1dc503f1045ccd6c8bd73277b18ba892befd1dc29e9b9a7822ed998
+size 7323310848

requirements.txt

@@ -0,0 +1,4 @@
+gpt4all
+langchain
+requests
+llama-cpp-python