Update

app.py

@@ -0,0 +1,15 @@
+"""Run qwen 7b.
+
+transformers 4.31.0
+"""
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation import GenerationConfig
+
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
+
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()
+model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
+
+response, history = model.chat(tokenizer, "你好", history=None)
+# response, history = model.chat(tokenizer, "你好", history=[])
+print(response)

requirements.txt

@@ -0,0 +1,12 @@
+transformers==4.31.0
+accelerate
+tiktoken
+einops
+flash-attention
+
+# git clone -b v1.0.8 https://github.com/Dao-AILab/flash-attention
+# cd flash-attention && pip install .
+# pip install csrc/layer_norm
+# pip install csrc/rotary
+
+torch  # 2.0.1