misc: update requirements.txt, polish docs, improve error logging (#234) (#234)

- feat: Improve ModelWorker's error printing
- chore: bump requirement.txt for guanaco support
- docs: fix some typos in Tutorials

docs/index.rst

@@ -33,11 +33,11 @@ Currently, we have released multiple key features, which are listed below to dem
 Getting Started
 -----------------
 | How to get started using DB-GPT to interact with your data and environment.
-- `Quickstart Guid <./getting_started/getting_started.html>`_
+- `Quickstart Guide <./getting_started/getting_started.html>`_
 
 | Concepts and terminology
 
-- `Concepts and terminology  <./getting_started/concepts.html>`_
+- `Concepts and Terminology  <./getting_started/concepts.html>`_
 
 | Coming soon...
 

docs/locales/zh_CN/LC_MESSAGES/getting_started/tutorials.po

@@ -34,19 +34,19 @@ msgid ""
 msgstr ""
 
 #: ../../getting_started/tutorials.md:8 b5e106a97bbd4467b071bb05d837d7d9
-msgid "Introduce"
+msgid "Introduction"
 msgstr ""
 
 #: ../../getting_started/tutorials.md:9 9df43436183d4b41a75a09fec15743d7
 #, fuzzy
 msgid "[What is DB-GPT](https://www.youtube.com/watch?v=QszhVJerc0I)"
 msgstr ""
-"###Introduce [什么是DB-"
+"###Introduction [什么是DB-"
 "GPT](https://www.bilibili.com/video/BV1SM4y1a7Nj/?buvid=551b023900b290f9497610b2155a2668&is_story_h5=false&mid=%2BVyE%2Fwau5woPcUKieCWS0A%3D%3D&p=1&plat_id=116&share_from=ugc&share_medium=iphone&share_plat=ios&share_session_id=5D08B533-82A4-4D40-9615-7826065B4574&share_source=GENERIC&share_tag=s_i&timestamp=1686307943&unique_k=bhO3lgQ&up_id=31375446)"
 "  by csunny (https://github.com/csunny/DB-GPT)"
 
 #: ../../getting_started/tutorials.md:11 3096811f862649bf84ff3cd29cdf14db
-msgid "Knowledge"
+msgid "Knowledge Base"
 msgstr "知识库"
 
 #: ../../getting_started/tutorials.md:13 ea00f3de8c754bf2950e735a2f14043a

pilot/configs/model_config.py

@@ -43,6 +43,8 @@ LLM_MODEL_CONFIG = {
     "guanaco-33b-merged": os.path.join(MODEL_PATH, "guanaco-33b-merged"),
     "falcon-40b": os.path.join(MODEL_PATH, "falcon-40b"),
     "gorilla-7b": os.path.join(MODEL_PATH, "gorilla-7b"),
+    # TODO Support baichuan-7b
+    # "baichuan-7b" : os.path.join(MODEL_PATH, "baichuan-7b"),
     "gptj-6b": os.path.join(MODEL_PATH, "ggml-gpt4all-j-v1.3-groovy.bin"),
     "proxyllm": "proxyllm",
 }

pilot/model/adapter.py

@@ -32,9 +32,14 @@ class BaseLLMAdaper:
         return True
 
     def loader(self, model_path: str, from_pretrained_kwargs: dict):
-        tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
+        tokenizer = AutoTokenizer.from_pretrained(
+            model_path, use_fast=False, trust_remote_code=True
+        )
         model = AutoModelForCausalLM.from_pretrained(
-            model_path, low_cpu_mem_usage=True, **from_pretrained_kwargs
+            model_path,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True,
+            **from_pretrained_kwargs,
         )
         return model, tokenizer
 
@@ -57,7 +62,7 @@ def get_llm_model_adapter(model_path: str) -> BaseLLMAdaper:
     raise ValueError(f"Invalid model adapter for {model_path}")
 
 
-# TODO support cpu? for practise we support gpt4all or chatglm-6b-int4?
+# TODO support cpu? for practice we support gpt4all or chatglm-6b-int4?
 
 
 class VicunaLLMAdapater(BaseLLMAdaper):

pilot/server/llmserver.py

@@ -5,6 +5,7 @@ import asyncio
 import json
 import os
 import sys
+import traceback
 
 import uvicorn
 from fastapi import BackgroundTasks, FastAPI, Request
@@ -89,10 +90,13 @@ class ModelWorker:
             ret = {"text": "**GPU OutOfMemory, Please Refresh.**", "error_code": 0}
             yield json.dumps(ret).encode() + b"\0"
         except Exception as e:
+            msg = "{}: {}".format(str(e), traceback.format_exc())
+
             ret = {
-                "text": f"**LLMServer Generate Error, Please CheckErrorInfo.**: {e}",
+                "text": f"**LLMServer Generate Error, Please CheckErrorInfo.**: {msg}",
                 "error_code": 0,
             }
+
             yield json.dumps(ret).encode() + b"\0"
 
     def get_embeddings(self, prompt):

requirements.txt

@@ -4,7 +4,7 @@ aiohttp==3.8.4
 aiosignal==1.3.1
 async-timeout==4.0.2
 attrs==22.2.0
-bitsandbytes==0.37.0
+bitsandbytes==0.39.0
 cchardet==2.1.7
 chardet==5.1.0
 contourpy==1.0.7
@@ -27,7 +27,7 @@ python-dateutil==2.8.2
 pyyaml==6.0
 tokenizers==0.13.2
 tqdm==4.64.1
-transformers==4.28.0
+transformers==4.30.0
 timm==0.6.13
 spacy==3.5.3
 webdataset==0.2.48