Instructions to use YouAreSpecialToMe/QST-70B-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YouAreSpecialToMe/QST-70B-checkpoint with Transformers:

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

pipe = pipeline("text-generation", model="YouAreSpecialToMe/QST-70B-checkpoint")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YouAreSpecialToMe/QST-70B-checkpoint")
model = AutoModelForCausalLM.from_pretrained("YouAreSpecialToMe/QST-70B-checkpoint", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YouAreSpecialToMe/QST-70B-checkpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YouAreSpecialToMe/QST-70B-checkpoint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YouAreSpecialToMe/QST-70B-checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YouAreSpecialToMe/QST-70B-checkpoint

SGLang

How to use YouAreSpecialToMe/QST-70B-checkpoint 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 "YouAreSpecialToMe/QST-70B-checkpoint" \
    --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": "YouAreSpecialToMe/QST-70B-checkpoint",
		"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 "YouAreSpecialToMe/QST-70B-checkpoint" \
        --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": "YouAreSpecialToMe/QST-70B-checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use YouAreSpecialToMe/QST-70B-checkpoint with Docker Model Runner:
```
docker model run hf.co/YouAreSpecialToMe/QST-70B-checkpoint
```

QST-70B-checkpoint

71.9 GB

Ctrl+K

2 contributors

History: 3 commits

SFconvertbot

Adding `safetensors` variant of this model

e1bf017 verified over 1 year ago

YouAreSpecialToMe
/

QST-70B-checkpoint

Detected Pickle imports (3)

Detected Pickle imports (5)

Detected Pickle imports (5)

Detected Pickle imports (4)

Detected Pickle imports (4)

Detected Pickle imports (5)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (7)

Pickle imports

Detected Pickle imports (9)