Instructions to use Ketak-ZoomRx/Prompt_Drug_opt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ketak-ZoomRx/Prompt_Drug_opt with Transformers:

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

pipe = pipeline("text-generation", model="Ketak-ZoomRx/Prompt_Drug_opt")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ketak-ZoomRx/Prompt_Drug_opt")
model = AutoModelForCausalLM.from_pretrained("Ketak-ZoomRx/Prompt_Drug_opt")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ketak-ZoomRx/Prompt_Drug_opt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ketak-ZoomRx/Prompt_Drug_opt

SGLang

How to use Ketak-ZoomRx/Prompt_Drug_opt 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 "Ketak-ZoomRx/Prompt_Drug_opt" \
    --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": "Ketak-ZoomRx/Prompt_Drug_opt",
		"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 "Ketak-ZoomRx/Prompt_Drug_opt" \
        --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": "Ketak-ZoomRx/Prompt_Drug_opt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ketak-ZoomRx/Prompt_Drug_opt with Docker Model Runner:
```
docker model run hf.co/Ketak-ZoomRx/Prompt_Drug_opt
```

Ketak-ZoomRx commited on Dec 4, 2023

Commit

f03766a

1 Parent(s): fd8535d

Upload cfg.yaml

Browse files

Files changed (1) hide show

cfg.yaml +2 -2

cfg.yaml CHANGED Viewed

@@ -26,11 +26,11 @@ dataset:
     personalize: false
     prompt_column:
     - instruction
-    system_column: prompt
     text_answer_separator: <|answer|>
     text_prompt_start: <|prompt|>
     text_system_start: <|system|>
-    train_dataframe: /app/h2o-llmstudio/data/user/Prompt_Data_5k/Prompt_Data_5k.csv
     validation_dataframe: None
     validation_size: 0.01
     validation_strategy: automatic

     personalize: false
     prompt_column:
     - instruction
+    system_column: Prompt
     text_answer_separator: <|answer|>
     text_prompt_start: <|prompt|>
     text_system_start: <|system|>
+    train_dataframe: /app/h2o-llmstudio/data/user/Drug_67k/Drug_67k.csv
     validation_dataframe: None
     validation_size: 0.01
     validation_strategy: automatic