Duplicate from AironHeart/llama2

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

app.py

@@ -0,0 +1,26 @@
+import torch
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
+
+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()
+
+
+def chat(message, history):
+    # prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
+    # 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):
+        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()

requirements.txt

@@ -0,0 +1,11 @@
+transformers
+diffusers
+accelerate
+xformers
+torch
+fairscale
+fire
+sentencepiece
+cpm_kernels
+protobuf 
+mdtex2html