Instructions to use dominguesm/tiny-random-canarim with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dominguesm/tiny-random-canarim with Transformers:

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

pipe = pipeline("text-generation", model="dominguesm/tiny-random-canarim")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dominguesm/tiny-random-canarim")
model = AutoModelForCausalLM.from_pretrained("dominguesm/tiny-random-canarim")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dominguesm/tiny-random-canarim with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dominguesm/tiny-random-canarim

SGLang

How to use dominguesm/tiny-random-canarim 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 "dominguesm/tiny-random-canarim" \
    --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": "dominguesm/tiny-random-canarim",
		"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 "dominguesm/tiny-random-canarim" \
        --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": "dominguesm/tiny-random-canarim",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dominguesm/tiny-random-canarim with Docker Model Runner:
```
docker model run hf.co/dominguesm/tiny-random-canarim
```

dominguesm commited on Nov 17, 2023

Commit

0eda889

1 Parent(s): f5f5306

Create README.md

Browse files

Files changed (1) hide show

README.md +13 -0

README.md ADDED Viewed

	@@ -0,0 +1,13 @@

+---
+license: cc-by-4.0
+---
+# tiny-random-canarim
+This is a tiny random Llama model derived from "dominguesm/canarim-7b".
+See [make_tiny_model.py](https://huggingface.co/stas/tiny-random-llama-2/blob/main/make_tiny_model.py) for how this was done.
+This is useful for functional testing (not quality generation, since its weights are random and the tokenizer has been shrunk to 3k items)
+Thanks to [Stas Bekman](https://huggingface.co/stas) for the code.