hello world

app.py

@@ -0,0 +1,29 @@
+from transformers import AutoTokenizer
+import transformers
+import torch
+import gradio as gr
+
+model= "PY007/TinyLlama-1.1B-step-50K-105b"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+
+sequences = pipeline(
+    'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.Chat Using TinyLlama',
+    do_sample=True,
+    top_k=10,
+    num_return_sequences=1,
+    repetition_penalty=1.5,
+    eos_token_id=tokenizer.eos_token_id,
+    max_length=500,
+)
+
+for seq in sequences:
+    print(f"Result :{seq['generated_text']}")

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+torch