fix(project): interlm run error (#69)

.gitignore

 .vscode/
 .idea/
+.egg/
 __pycache__/
 *.egg-info/
 workspace/

README.md

@@ -62,7 +62,7 @@ Below are quick steps for installation:
 ```shell
 conda create -n lmdeploy python=3.10
 conda activate lmdeploy
-git clone clone https://github.com/InternLM/lmdeploy.git
+git clone https://github.com/InternLM/lmdeploy.git
 cd lmdeploy
 pip install -e .
 ```

lmdeploy/turbomind/chat.py

@@ -19,7 +19,7 @@ def main(model_name, model_path, session_id: int = 1):
     tm_model = tm.TurboMind(model_path)
     generator = tm_model.create_instance()
     tokenizer_model_path = osp.join(model_path, 'triton_models', 'tokenizer')
-    tokenizer = AutoTokenizer.from_pretrained(tokenizer_model_path)
+    tokenizer = AutoTokenizer.from_pretrained(tokenizer_model_path, trust_remote_code=True)
     model = MODELS.get(model_name)()
 
     nth_round = 1

requirements.txt

@@ -5,3 +5,4 @@ safetensors
 setuptools
 transformers<4.30.0
 tritonclient==2.33.0
+pybind11