OpenMOSS-Team
/

moss-moon-003-sft-int4

Text Generation

Model card Files Files and versions

Instructions to use OpenMOSS-Team/moss-moon-003-sft-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMOSS-Team/moss-moon-003-sft-int4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="OpenMOSS-Team/moss-moon-003-sft-int4", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenMOSS-Team/moss-moon-003-sft-int4", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

How to use OpenMOSS-Team/moss-moon-003-sft-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMOSS-Team/moss-moon-003-sft-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/moss-moon-003-sft-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenMOSS-Team/moss-moon-003-sft-int4

How to use OpenMOSS-Team/moss-moon-003-sft-int4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OpenMOSS-Team/moss-moon-003-sft-int4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/moss-moon-003-sft-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OpenMOSS-Team/moss-moon-003-sft-int4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/moss-moon-003-sft-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenMOSS-Team/moss-moon-003-sft-int4 with Docker Model Runner:
```
docker model run hf.co/OpenMOSS-Team/moss-moon-003-sft-int4
```

Single GPU时：No module named 'transformers_modules.moss-moon-003-sft-int4.custom_autotune'

#4

by xiabo0816 - opened Apr 26, 2023

root@bogon ~/m/MOSS (main)# python3 
Python 3.9.16 (main, Mar  8 2023, 14:00:05)
[GCC 11.2.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("/root/moss/moss-moon-003-sft-int4", trust_remote_code=True)
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
>>> model = AutoModelForCausalLM.from_pretrained("/root/moss/moss-moon-003-sft-int4", trust_remote_code=True).half().cuda()
Explicitly passing a `revision` is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/root/miniconda3/envs/chatglm/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 466, in from_pretrained
    return model_class.from_pretrained(
  File "/root/miniconda3/envs/chatglm/lib/python3.9/site-packages/transformers/modeling_utils.py", line 2498, in from_pretrained
    model = cls(config, *model_args, **model_kwargs)
  File "/root/.cache/huggingface/modules/transformers_modules/moss-moon-003-sft-int4/modeling_moss.py", line 608, in __init__
    self.quantize(config.wbits, config.groupsize)
  File "/root/.cache/huggingface/modules/transformers_modules/moss-moon-003-sft-int4/modeling_moss.py", line 732, in quantize
    from .quantization import quantize_with_gptq
  File "/root/.cache/huggingface/modules/transformers_modules/moss-moon-003-sft-int4/quantization.py", line 8, in <module>
    from .custom_autotune import *
ModuleNotFoundError: No module named 'transformers_modules.moss-moon-003-sft-int4.custom_autotune'
>

已经git clone 过MOSS.git，也cd进来，还是报：

ModuleNotFoundError: No module named 'transformers_modules.moss-moon-003-sft-int4.custom_autotune'

是仍然有文件放错位置了吗？

在多加了一个斜线/之后：

model = AutoModelForCausalLM.from_pretrained("/root/moss/moss-moon-003-sft-int4/", trust_remote_code=True).half().cuda()

报错改变了：

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/root/miniconda3/envs/chatglm/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 466, in from_pretrained
    return model_class.from_pretrained(
  File "/root/miniconda3/envs/chatglm/lib/python3.9/site-packages/transformers/modeling_utils.py", line 2498, in from_pretrained
    model = cls(config, *model_args, **model_kwargs)
  File "/root/.cache/huggingface/modules/transformers_modules/modeling_moss.py", line 608, in __init__
    self.quantize(config.wbits, config.groupsize)
  File "/root/.cache/huggingface/modules/transformers_modules/modeling_moss.py", line 732, in quantize
    from .quantization import quantize_with_gptq
  File "/root/.cache/huggingface/modules/transformers_modules/quantization.py", line 8, in <module>
    from .custom_autotune import *
ModuleNotFoundError: No module named 'transformers_modules.custom_autotune'

Same error

EndlessnessSoul

我直接把 custom_autotune.py Copy到"/root/.cache/huggingface/modules/transformers_modules/"

试试这个

import sys
sys.path.append('/root/.cache/huggingface/modules')

我用的是Tesla P40，换成fnlp/moss-moon-003-sft就很正常了，感觉是显卡和INT4不太搭？

试试这个

import sys
sys.path.append('/root/.cache/huggingface/modules')

我这里尝试了之后，还是不行😢

我直接把 custom_autotune.py Copy到"/root/.cache/huggingface/modules/transformers_modules/"

我这里尝试了之后，也还是不行

我直接把 custom_autotune.py Copy到"/root/.cache/huggingface/modules/transformers_modules/"

我这里尝试了之后，也还是不行

https://github.com/yhyu13/MOSS/blob/dev/local_setup.sh

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment