Instructions to use Hack90/virus_pythia_31_1024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hack90/virus_pythia_31_1024 with Transformers:

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

pipe = pipeline("text-generation", model="Hack90/virus_pythia_31_1024")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hack90/virus_pythia_31_1024")
model = AutoModelForCausalLM.from_pretrained("Hack90/virus_pythia_31_1024")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Hack90/virus_pythia_31_1024 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hack90/virus_pythia_31_1024"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hack90/virus_pythia_31_1024",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hack90/virus_pythia_31_1024

SGLang

How to use Hack90/virus_pythia_31_1024 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 "Hack90/virus_pythia_31_1024" \
    --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": "Hack90/virus_pythia_31_1024",
		"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 "Hack90/virus_pythia_31_1024" \
        --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": "Hack90/virus_pythia_31_1024",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hack90/virus_pythia_31_1024 with Docker Model Runner:
```
docker model run hf.co/Hack90/virus_pythia_31_1024
```

Hack90 commited on Mar 21, 2024

Commit

236f06d

verified ·

1 Parent(s): e16c918

Update tokenizer.json

Browse files

Files changed (1) hide show

tokenizer.json +5 -5

tokenizer.json CHANGED Viewed

@@ -74,11 +74,11 @@
       "<|endoftext|>": 1,
       "<|padding|>": 1,
       "<|unknown|>" : 2,
-      "a": 28,
-      "c": 29,
-      "g": 30,
-      "t": 31,
-      "n": 32,
       "<|beginoftext|>" : 0
     }, "merges":[] }}

       "<|endoftext|>": 1,
       "<|padding|>": 1,
       "<|unknown|>" : 2,
+      "a": 3,
+      "c": 4,
+      "g": 5,
+      "t": 6,
+      "n": 7,
       "<|beginoftext|>" : 0
     }, "merges":[] }}