codefuse-ai / codefuse-devops-model Goto Github PK

When do you support fastchat? Currently, there is an API exception when deploying fastchat.

python -m fastchat.serve.vllm_worker --model-names kagentlms_qwen_7b_mat --model-path /data/model/modelscope_hub/qwen/kagentlms_qwen_7b_mat --dtype half --controller-address http://$IP:21001 --trust-remote-code --enforce-eager
run ok.
python -m fastchat.serve.vllm_worker --model-names CodeFuse-DevOps-Model-14B-Chat --model-path /data/model/modelscope_hub/codefuse-ai/CodeFuse-DevOps-Model-14B-Chat --dtype half --controller-address http://$IP:21001 --max-log-len=2000 --trust-remote-code --enforce-eager
run error with lots of prompts unneed .
2024-01-03 16:48:57 | INFO | stdout | INFO: 127.0.0.1:52652 - "POST /worker_generate_stream HTTP/1.1" 200 OK
INFO 01-03 16:48:57 async_llm_engine.py:379] Received request 4df14bc8f28944399134d3e8204757ad: prompt: "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activi", sampling params: SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.7, top_p=1.0, top_k=-1.0, min_p=0.0, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['<|im_end|>', '###'], stop_token_ids=[151645], include_stop_str_in_output=False, ignore_eos=False, max_tokens=512, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True), prompt token ids: None.
WARNING 01-03 16:48:57 scheduler.py:161] Input prompt (456 tokens) is too long and exceeds the capacity of block_manager
INFO 01-03 16:48:57 async_llm_engine.py:111] Finished request 4df14bc8f28944399134d3e8204757ad.
INFO 01-03 16:48:57 async_llm_engine.py:134] Aborted request 4df14bc8f28944399134d3e8204757ad.

conda 环境
python 3.10.13
相关依赖
accelerate 0.25.0
aiofiles 23.2.1
aiohttp 3.9.1
aioprometheus 23.12.0
aiosignal 1.3.1
altair 5.2.0
anyio 4.2.0
async-timeout 4.0.3
attrs 23.1.0
beautifulsoup4 4.12.2
Brotli 1.1.0
bs4 0.0.1
certifi 2023.11.17
cffi 1.16.0
charset-normalizer 3.3.2
click 8.1.7
contourpy 1.2.0
cryptography 41.0.7
cycler 0.12.1
docstring-parser 0.15
duckduckgo-search 3.8.4
ephem 4.1.4
exceptiongroup 1.2.0
fastapi 0.108.0
ffmpy 0.3.1
filelock 3.13.1
fonttools 4.47.0
frozenlist 1.4.1
fschat 0.2.34
fsspec 2023.12.2
gradio 3.50.2
gradio_client 0.6.1
h11 0.14.0
h2 4.1.0
hpack 4.0.0
httpcore 1.0.2
httptools 0.6.1
httpx 0.26.0
huggingface-hub 0.20.1
hyperframe 6.0.1
idna 3.6
importlib-resources 6.1.1
Jinja2 3.1.2
jsonschema 4.20.0
jsonschema-specifications 2023.12.1
kiwisolver 1.4.5
kwaiagents 0.0.1 /data/jupyter_multi_users/dessun/ks_agent/KwaiAgents-main
libretranslatepy 2.1.1
lunar-python 1.3.2
lxml 4.9.4
markdown-it-py 3.0.0
markdown2 2.4.12
MarkupSafe 2.1.3
matplotlib 3.8.2
mdurl 0.1.2
mpmath 1.3.0
msgpack 1.0.7
multidict 6.0.4
networkx 3.2.1
nh3 0.2.15
ninja 1.11.1.1
numpy 1.26.2
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
nvidia-cuda-nvrtc-cu12 12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12 8.9.2.26
nvidia-cufft-cu12 11.0.2.54
nvidia-curand-cu12 10.3.2.106
nvidia-cusolver-cu12 11.4.5.107
nvidia-cusparse-cu12 12.1.0.106
nvidia-nccl-cu12 2.18.1
nvidia-nvjitlink-cu12 12.3.101
nvidia-nvtx-cu12 12.1.105
openai 0.27.8
orjson 3.9.10
outcome 1.3.0.post0
packaging 23.2
pandas 2.1.4
peft 0.7.1
Pillow 10.1.0
pip 23.3.1
prompt-toolkit 3.0.43
protobuf 4.25.1
psutil 5.9.7
pyarrow 14.0.2
pycparser 2.21
pydantic 1.10.13
pydub 0.25.1
Pygments 2.17.2
pyOpenSSL 22.0.0
pyparsing 3.1.1
PySocks 1.7.1
python-dateutil 2.8.2
python-dotenv 1.0.0
python-multipart 0.0.6
pytz 2023.3.post1
PyYAML 6.0.1
quantile-python 1.1
ray 2.9.0
referencing 0.32.0
regex 2023.12.25
requests 2.31.0
rich 13.7.0
rpds-py 0.16.2
safetensors 0.4.1
selenium 4.1.4
semantic-version 2.10.0
sentencepiece 0.1.99
setuptools 68.2.2
shortuuid 1.0.11
six 1.16.0
sniffio 1.3.0
socksio 1.0.0
sortedcontainers 2.4.0
soupsieve 2.5
starlette 0.32.0.post1
svgwrite 1.4.3
sympy 1.12
tiktoken 0.5.2
tokenizers 0.15.0
toolz 0.12.0
torch 2.1.2
tqdm 4.66.1
transformers 4.36.2
translate 3.6.1
trio 0.23.2
trio-websocket 0.11.1
triton 2.1.0
typing_extensions 4.9.0
tzdata 2023.3
urllib3 1.26.18
urllib3-secure-extra 0.1.0
uvicorn 0.25.0
uvloop 0.19.0
vllm 0.2.6
watchfiles 0.21.0
wavedrom 2.0.3.post3
wcwidth 0.2.12
webdriver-manager 3.8.6
websockets 11.0.3
wheel 0.41.2
wsproto 1.2.0
xformers 0.0.23.post1
yarl 1.9.4

for example, how to pass args for local model path?
also, I got error when I run web_demo.py

python3 web_demo.py 
[2023-11-20 15:27:44,026] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/venv/lib/python3.9/site-packages/trl/trainer/ppo_config.py:141: UserWarning: The `optimize_cuda_cache` arguement will be deprecated soon, please use `optimize_device_cache` instead.
  warnings.warn(
Traceback (most recent call last):
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/web_demo.py", line 1, in <module>
    from llmtuner import create_web_demo
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/llmtuner/__init__.py", line 5, in <module>
    from llmtuner.tuner import export_model, run_exp
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/llmtuner/tuner/__init__.py", line 1, in <module>
    from llmtuner.tuner.tune import export_model, run_exp
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/llmtuner/tuner/tune.py", line 9, in <module>
    from llmtuner.tuner.ppo import run_ppo
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/llmtuner/tuner/ppo/__init__.py", line 1, in <module>
    from llmtuner.tuner.ppo.workflow import run_ppo
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/llmtuner/tuner/ppo/workflow.py", line 14, in <module>
    from llmtuner.tuner.ppo.trainer import PPOPeftTrainer
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/llmtuner/tuner/ppo/trainer.py", line 27, in <module>
    class PPOPeftTrainer(PPOTrainer, PeftTrainer):
  File "/DATA/disk0/CodeFuse/CodeFuse-DevOps-Model/src/llmtuner/tuner/ppo/trainer.py", line 198, in PPOPeftTrainer
    @PPODecorators.empty_cuda_cache()
AttributeError: type object 'PPODecorators' has no attribute 'empty_cuda_cache'

https://huggingface.co/codefuse-ai/CodeFuse-DevOps-Model-14B-Chat