Duplicate from FredZhang7/chat-test

Co-authored-by: Fred Zhang <FredZhang7@users.noreply.huggingface.co>

.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 +1,14 @@
+---
+title: Chat Test
+emoji: 📚
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 3.36.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: FredZhang7/chat-test
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,33 @@
+import os 
+os.system("pip install --upgrade torch transformers sentencepiece scipy cpm_kernels accelerate bitsandbytes")
+
+
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
+# model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_v2_w")
+model = AutoModelForCausalLM.from_pretrained("openchat/openchat_v2_w", load_in_8bit_fp32_cpu_offload=True, load_in_8bit=True)
+model.float()
+model = model.eval()
+
+model_path = model.config._dict['model_name_or_path']
+model_size_gb = os.path.getsize(model_path) / (1024 * 1024 * 1024)
+
+print(f"The model '{model_name}' is taking approximately {model_size_gb:.2f} GB of disk space.")
+
+# with gr.Blocks() as demo:
+#     chatbot = gr.Chatbot()
+#     msg = gr.Textbox()
+#     clear = gr.ClearButton([msg, chatbot])
+
+#     def respond(message, chat_history):
+#         response, chat_history = model.chat(tokenizer, message, history=chat_history, temperature=0.7, repetition_penalty=1.2, max_length=128)
+#         chat_history.append((message, response))
+#         return "", chat_history
+
+#     msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+# if __name__ == "__main__":
+#     demo.launch()

ultrachat-13B-test.py

@@ -0,0 +1,27 @@
+import os
+os.system("pip install llama-cpp-python")
+
+from gradio import Interface, Textbox, Slider
+import requests
+from llama_cpp import Llama
+
+url = "https://huggingface.co/TheBloke/UltraLM-13B-GGML/resolve/main/ultralm-13b.ggmlv3.q4_0.bin"
+
+response = requests.get(url)
+with open("ultralm-13b.ggmlv3.q4_0.bin", "wb") as f:
+    f.write(response.content)
+
+# os.system("pwd")
+# os.system("ls")
+
+llm = Llama(model_path="ultralm-13b.ggmlv3.q4_0.bin", n_ctx=2048)
+
+def generate_text(prompt, temperature, max_length):
+    prompt_template=f'''USER: {prompt}
+ASSISTANT:'''
+    output = llm.create_completion(prompt_template, temperature=temperature, max_tokens=max_length, echo=True, stop=["USER:"])
+    print(output)
+    return output
+
+
+Interface(fn=generate_text, inputs=[Textbox(type="text", lines=10), Slider(minimum=0, maximum=2, step=0.1, value=0.7), Slider(minimum=1, maximum=2048, step=2, value=256)], outputs=Textbox(type="text", lines=20), title="UltraChat 13B Text Generation", description="Enter a prompt to generate text.").launch()

ultrachat-13b-performance.md

@@ -0,0 +1,7 @@
+Default Config, with temperature=0.7 and max_tokens=256
+
+| Response Time  |  Prompt                | 
+|----------------|------------------------|
+| 350+ seconds   |  "Hi"                  | 
+| 1000+ seconds  |  an inappropriate word | 
+|  N/A  |  https://flowgpt.com/prompt/af5bcff8-899e-4d79-a968-c4a3b38c5954?isModal=true  |