Instructions to use tarekziade/test-quantize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tarekziade/test-quantize with Transformers:

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

pipe = pipeline("image-text-to-text", model="tarekziade/test-quantize")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("tarekziade/test-quantize")
model = AutoModelForImageTextToText.from_pretrained("tarekziade/test-quantize")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tarekziade/test-quantize with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tarekziade/test-quantize

SGLang

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

Docker Model Runner
How to use tarekziade/test-quantize with Docker Model Runner:
```
docker model run hf.co/tarekziade/test-quantize
```

tarekziade HF Staff commited on Jun 5, 2024

Commit

51b1210

verified ·

1 Parent(s): 6a08494

Update generation_config.json

Browse files

Files changed (1) hide show

generation_config.json +2 -2

generation_config.json CHANGED Viewed

@@ -5,10 +5,10 @@
   "eos_token_id": 50256,
   "max_length": 50,
   "no_repeat_ngram_size": 2,
-  "num_beams": 10,
   "pad_token_id": 50256,
   "repetition_penalty": 1.2,
   "transformers_version": "4.33.2",
-  "seed": 42,
   "temperature": 0.7
 }

   "eos_token_id": 50256,
   "max_length": 50,
   "no_repeat_ngram_size": 2,
+  "num_beams": 2,
   "pad_token_id": 50256,
   "repetition_penalty": 1.2,
   "transformers_version": "4.33.2",
+  "seed": 12,
   "temperature": 0.7
 }