Instructions to use dram-conflict/test_scripts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dram-conflict/test_scripts with Transformers:

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

pipe = pipeline("text-generation", model="dram-conflict/test_scripts")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dram-conflict/test_scripts")
model = AutoModelForCausalLM.from_pretrained("dram-conflict/test_scripts")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dram-conflict/test_scripts with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dram-conflict/test_scripts

SGLang

How to use dram-conflict/test_scripts 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 "dram-conflict/test_scripts" \
    --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": "dram-conflict/test_scripts",
		"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 "dram-conflict/test_scripts" \
        --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": "dram-conflict/test_scripts",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dram-conflict/test_scripts with Docker Model Runner:
```
docker model run hf.co/dram-conflict/test_scripts
```

AlekseyKorshuk commited on Nov 18, 2022

Commit

62aab8f

1 Parent(s): 2e5b310

Commit from colab

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
training_args.bin +1 -1

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297893ca1981e10aff05a597301e288b34c86b02a4156847b08b2530e36e5d5a
 size 1444566873

 version https://git-lfs.github.com/spec/v1
+oid sha256:d9f9872b658207e78593b489a9d4d5979087a0dc59be998fe5d8b4e20516f8e3
 size 1444566873

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ed6ea1796e1599215ce4f893acdbb46e085ebe84042b9d7041fbc40a2119d1
 size 3375

 version https://git-lfs.github.com/spec/v1
+oid sha256:b71de44df04bb432a6103c905ce6e7c7e9b6f70e29ea4a6183ef69d44361c18c
 size 3375