Instructions to use TheBloke/guanaco-33B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/guanaco-33B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/guanaco-33B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/guanaco-33B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/guanaco-33B-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/guanaco-33B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/guanaco-33B-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/guanaco-33B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/guanaco-33B-GPTQ

SGLang

How to use TheBloke/guanaco-33B-GPTQ 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 "TheBloke/guanaco-33B-GPTQ" \
    --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": "TheBloke/guanaco-33B-GPTQ",
		"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 "TheBloke/guanaco-33B-GPTQ" \
        --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": "TheBloke/guanaco-33B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/guanaco-33B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/guanaco-33B-GPTQ
```

Error no file named pytorch_model.bin

by Boffy - opened May 26, 2023

Discussion

Boffy

May 26, 2023

4090 so I don't get the memory issue.. what am I missing here?

INFO:Loading guanaco-33B-GPTQ...
WARNING:Auto-assiging --gpu-memory 23 for your GPU to try to prevent out-of-memory errors. You can manually set other values.
Traceback (most recent call last):
File "C:\Projects\AI\text-generation-webui\server.py", line 1087, in
shared.model, shared.tokenizer = load_model(shared.model_name)
File "C:\Projects\AI\text-generation-webui\modules\models.py", line 95, in load_model
output = load_func(model_name)
File "C:\Projects\AI\text-generation-webui\modules\models.py", line 223, in huggingface_loader
model = LoaderClass.from_pretrained(checkpoint, **params)
File "C:\Projects\AI\installer_files\env\lib\site-packages\transformers\models\auto\auto_factory.py", line 471, in from_pretrained
return model_class.from_pretrained(
File "C:\Projects\AI\installer_files\env\lib\site-packages\transformers\modeling_utils.py", line 2405, in from_pretrained
raise EnvironmentError(
OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory models\guanaco-33B-GPTQ.

TheBloke

Owner May 26, 2023

You need to set the GPTQ parameters - please see the instructions in the README

Boffy

May 26, 2023

I tried that.. it doesn't like it the error below ...the other model 'Guanaco-33B-4bit' works fine so will use that.. not sure on the performance difference?

Traceback (most recent call last): File “C:\Projects\AI\text-generation-webui\server.py”, line 71, in load_model_wrapper shared.model, shared.tokenizer = load_model(shared.model_name) File “C:\Projects\AI\text-generation-webui\modules\models.py”, line 95, in load_model output = load_func(model_name) File “C:\Projects\AI\text-generation-webui\modules\models.py”, line 289, in GPTQ_loader model = modules.GPTQ_loader.load_quantized(model_name) File “C:\Projects\AI\text-generation-webui\modules\GPTQ_loader.py”, line 177, in load_quantized model = load_quant(str(path_to_model), str(pt_path), shared.args.wbits, shared.args.groupsize, kernel_switch_threshold=threshold) File “C:\Projects\AI\text-generation-webui\modules\GPTQ_loader.py”, line 84, in _load_quant model.load_state_dict(safe_load(checkpoint), strict=False) File “C:\Projects\AI\installer_files\env\lib\site-packages\safetensors\torch.py”, line 261, in load_file result[k] = f.get_tensor(k) RuntimeError: [enforce fail at C:\cb\pytorch_1000000000000\work\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 425984000 bytes.

Boffy

May 26, 2023

never mind.. spoke to soon.. restarted it and it loaded fine

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