Update minimal requirements.txt

README.md

@@ -1,13 +1,12 @@
 ---
-title: Stabilityai StableBeluga2
+title: gradio-interface-tryout
 emoji: 🚀
 colorFrom: yellow
 colorTo: gray
 sdk: gradio
 sdk_version: 3.39.0
 app_file: app.py
-pinned: false
-duplicated_from: AironHeart/llama2
+pinned: true
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,14 +1,19 @@
-import torch
+# import torch
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+# device = "cuda" if torch.cuda.is_available() else "cpu"
+
 # tokenizer = AutoTokenizer.from_pretrained("stabilityai/StableBeluga2", use_fast=False)
 # model = AutoModelForCausalLM.from_pretrained("stabilityai/StableBeluga2", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
 # system_prompt = "### System:\nYou are Stable Beluga, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
 # pipeline = pipeline(task="text-generation", model="meta-llama/Llama-2-7b")
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
-chat_model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).float()
+tokenizer = AutoTokenizer.from_pretrained(
+    "THUDM/chatglm2-6b-int4", trust_remote_code=True
+)
+chat_model = AutoModel.from_pretrained(
+    "THUDM/chatglm2-6b-int4", trust_remote_code=True
+).float()
 
 
 def chat(message, history):
@@ -16,11 +21,14 @@ def chat(message, history):
     # inputs = tokenizer(prompt, return_tensors="pt").to(device=device)
     # output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
     # return tokenizer.decode(output[0], skip_special_tokens=True)
-    for response, history in chat_model.stream_chat(tokenizer, message, history, max_length=2048, top_p=0.7, temperature=0.95):
+    for response, history in chat_model.stream_chat(
+        tokenizer, message, history, max_length=2048, top_p=0.7, temperature=0.95
+    ):
         yield response
 
 
-gr.ChatInterface(chat,
-                 title="StableBeluga2 (Enjoy various AI tools and applications at aironheart.com For FREE!)",
-                 description="Enjoy various AI tools and applications at aironheart.com/explore For FREE!",
-                 ).queue(1).launch()
+gr.ChatInterface(
+    chat,
+    title="StableBeluga2 (Enjoy various AI tools and applications at aironheart.com For FREE!)",
+    description="Enjoy various AI tools and applications at aironheart.com/explore For FREE!",
+).queue(1).launch()

requirements.txt

@@ -1,11 +1,11 @@
 transformers
-diffusers
-accelerate
-xformers
-torch
-fairscale
-fire
-sentencepiece
-cpm_kernels
-protobuf 
-mdtex2html
+# diffusers
+# accelerate
+# xformers
+# torch
+# fairscale
+# fire
+# sentencepiece
+# cpm_kernels
+# protobuf
+# mdtex2html