Instructions to use superAVTR/tinizong-46M_v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use superAVTR/tinizong-46M_v1.1 with Transformers:

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

pipe = pipeline("text-generation", model="superAVTR/tinizong-46M_v1.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("superAVTR/tinizong-46M_v1.1")
model = AutoModelForCausalLM.from_pretrained("superAVTR/tinizong-46M_v1.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use superAVTR/tinizong-46M_v1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "superAVTR/tinizong-46M_v1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "superAVTR/tinizong-46M_v1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/superAVTR/tinizong-46M_v1.1

SGLang

How to use superAVTR/tinizong-46M_v1.1 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 "superAVTR/tinizong-46M_v1.1" \
    --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": "superAVTR/tinizong-46M_v1.1",
		"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 "superAVTR/tinizong-46M_v1.1" \
        --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": "superAVTR/tinizong-46M_v1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use superAVTR/tinizong-46M_v1.1 with Docker Model Runner:
```
docker model run hf.co/superAVTR/tinizong-46M_v1.1
```

superAVTR commited on 5 days ago

Commit

7c955a3

verified ·

1 Parent(s): 75b8d95

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -92,7 +92,9 @@ These results should be interpreted in the context of the model's small size (~4
 The evaluation was run with:
 ```bash
-lm_eval \
   --model hf \
   --model_args pretrained=superAVTR/tinizong-46M,dtype=float \
   --tasks lambada_openai,hellaswag,piqa,arc_easy \

 The evaluation was run with:
 ```bash
+#!pip install lm-eval
+!lm_eval \
   --model hf \
   --model_args pretrained=superAVTR/tinizong-46M,dtype=float \
   --tasks lambada_openai,hellaswag,piqa,arc_easy \