Instructions to use mayaeary/pygmalion-6b-4bit-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mayaeary/pygmalion-6b-4bit-128g with Transformers:

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

pipe = pipeline("text-generation", model="mayaeary/pygmalion-6b-4bit-128g")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mayaeary/pygmalion-6b-4bit-128g")
model = AutoModelForCausalLM.from_pretrained("mayaeary/pygmalion-6b-4bit-128g")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mayaeary/pygmalion-6b-4bit-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mayaeary/pygmalion-6b-4bit-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mayaeary/pygmalion-6b-4bit-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mayaeary/pygmalion-6b-4bit-128g

SGLang

How to use mayaeary/pygmalion-6b-4bit-128g 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 "mayaeary/pygmalion-6b-4bit-128g" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mayaeary/pygmalion-6b-4bit-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mayaeary/pygmalion-6b-4bit-128g" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mayaeary/pygmalion-6b-4bit-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mayaeary/pygmalion-6b-4bit-128g with Docker Model Runner:
```
docker model run hf.co/mayaeary/pygmalion-6b-4bit-128g
```

Don't load in oobabooga webui (gtx 1660 ti, intel core i5)

by Vlagamer - opened Apr 13, 2023

Discussion

Vlagamer

Apr 13, 2023

i know what isnt a github but (Starting the web UI...

===================================BUG REPORT===================================

Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues

================================================================================

CUDA SETUP: CUDA runtime path found: D:\Games\oobabooga-windows\installer_files\env\bin\cudart64_110.dll

CUDA SETUP: Highest compute capability among GPUs detected: 7.5

CUDA SETUP: Detected CUDA version 117

CUDA SETUP: Loading binary D:\Games\oobabooga-windows\installer_files\env\lib\site-packages\bitsandbytes\libbitsandbytes_cuda117.dll...

Loading mayaeary_pygmalion-6b_dev-4bit-128g...

Found the following quantized model: models\mayaeary_pygmalion-6b_dev-4bit-128g\pygmalion-6b_dev-4bit-128g.safetensors

Loading model ...

D:\Games\oobabooga-windows\installer_files\env\lib\site-packages\safetensors\torch.py:99: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()

with safe_open(filename, framework="pt", device=device) as f:

D:\Games\oobabooga-windows\installer_files\env\lib\site-packages\torch\_utils.py:776: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()

return self.fget.__get__(instance, owner)()

D:\Games\oobabooga-windows\installer_files\env\lib\site-packages\torch\storage.py:899: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()

storage = cls(wrap_storage=untyped_storage) ) i got this error tell me what to do in fact I have these configurations --wbits 4 --groupsize 128 --extensions api

mayaeary

Owner Apr 14, 2023

•

edited Apr 14, 2023

It isn't errors, it just warnings. You should be able to use model without problems.

WAitester79

Apr 16, 2023

I have this error loading the model

Traceback (most recent call last):
File "C:\AIweb\oobabooga-windows\text-generation-webui\server.py", line 85, in load_model_wrapper
shared.model, shared.tokenizer = load_model(shared.model_name)
File "C:\AIweb\oobabooga-windows\text-generation-webui\modules\models.py", line 188, in load_model
tokenizer = AutoTokenizer.from_pretrained(Path(f"{shared.args.model_dir}/{shared.model_name}/"))
File "C:\AIweb\oobabooga-windows\installer_files\env\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 702, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
File "C:\AIweb\oobabooga-windows\installer_files\env\lib\site-packages\transformers\tokenization_utils_base.py", line 1811, in from_pretrained
return cls._from_pretrained(
File "C:\AIweb\oobabooga-windows\installer_files\env\lib\site-packages\transformers\tokenization_utils_base.py", line 1841, in _from_pretrained
slow_tokenizer = (cls.slow_tokenizer_class)._from_pretrained(
File "C:\AIweb\oobabooga-windows\installer_files\env\lib\site-packages\transformers\tokenization_utils_base.py", line 1965, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "C:\AIweb\oobabooga-windows\installer_files\env\lib\site-packages\transformers\models\gpt2\tokenization_gpt2.py", line 188, in init
with open(vocab_file, encoding="utf-8") as vocab_handle:
TypeError: expected str, bytes or os.PathLike object, not NoneType

brucethemoose

Apr 20, 2023

That means the model isn't downloaded properly, you have to clone/download the whole folder so that it matches this repo exactly.

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