Instructions to use hf-internal-testing/tiny-xlm-roberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-xlm-roberta with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/tiny-xlm-roberta")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-xlm-roberta")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/tiny-xlm-roberta")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-xlm-roberta with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-xlm-roberta

SGLang

How to use hf-internal-testing/tiny-xlm-roberta 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 "hf-internal-testing/tiny-xlm-roberta" \
    --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": "hf-internal-testing/tiny-xlm-roberta",
		"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 "hf-internal-testing/tiny-xlm-roberta" \
        --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": "hf-internal-testing/tiny-xlm-roberta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-xlm-roberta with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-xlm-roberta
```

stas commited on Jul 8, 2021

Commit

d361e26

1 Parent(s): c652096

updates

Browse files

Files changed (1) hide show

make-tiny-xlm-roberta.py +5 -4

make-tiny-xlm-roberta.py CHANGED Viewed

@@ -33,13 +33,14 @@
 # 4. start with some pre-existing script from one of the https://huggingface.co/hf-internal-testing/ tiny model repos, e.g.
 # wget https://huggingface.co/hf-internal-testing/tiny-xlm-roberta/raw/main/make-tiny-xlm-roberta.py
 # chmod a+x ./make-tiny-xlm-roberta.py
 #
 # 5. automatically rename things from the old names to new ones
 # perl -pi -e 's|MT5|XLMRoberta|g' make-tiny-xlm-roberta.py
 # perl -pi -e 's|mt5|xlm-roberta|g' make-tiny-xlm-roberta.py
 #
 # 6. edit and re-run this script while fixing it up
-# ./make-tiny-xlm-roberta.py .
 #
 # 7. add/commit/push
 # git add *
@@ -53,7 +54,7 @@
 # cd tiny-xlm-roberta
 #
 # 2. edit and re-run this script after doing whatever changes are needed
-# ./make-tiny-xlm-roberta.py .
 #
 # 3. commit/push
 # git commit -m "new tiny model"
@@ -72,12 +73,12 @@ os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
 mname_orig = "xlm-roberta-base"
 mname_tiny = "tiny-xlm-roberta"
-tmp_dir = f"/tmp/{mname_tiny}"
 ### Tokenizer
 # Shrink the orig vocab to keep things small
 vocab_keep_items = 5000
 vocab_orig_path = f"{tmp_dir}/sentencepiece.bpe.model"
 vocab_short_path = f"{tmp_dir}/spiece-short.model"
 if 1: # set to 0 to skip this after running once to speed things up during tune up
@@ -143,6 +144,6 @@ tokenizer_fast_tiny.save_pretrained(".")
 readme = "README.md"
 if not os.path.exists(readme):
     with open(readme, "w") as f:
-        f.write(f"This is a tiny random {mname_tiny} model to be used for basic testing.")
 print(f"Generated {mname_tiny}")

 # 4. start with some pre-existing script from one of the https://huggingface.co/hf-internal-testing/ tiny model repos, e.g.
 # wget https://huggingface.co/hf-internal-testing/tiny-xlm-roberta/raw/main/make-tiny-xlm-roberta.py
 # chmod a+x ./make-tiny-xlm-roberta.py
+# mv ./make-tiny-xlm-roberta.py ./make-tiny-xlm-roberta.py
 #
 # 5. automatically rename things from the old names to new ones
 # perl -pi -e 's|MT5|XLMRoberta|g' make-tiny-xlm-roberta.py
 # perl -pi -e 's|mt5|xlm-roberta|g' make-tiny-xlm-roberta.py
 #
 # 6. edit and re-run this script while fixing it up
+# ./make-tiny-xlm-roberta.py
 #
 # 7. add/commit/push
 # git add *
 # cd tiny-xlm-roberta
 #
 # 2. edit and re-run this script after doing whatever changes are needed
+# ./make-tiny-xlm-roberta.py
 #
 # 3. commit/push
 # git commit -m "new tiny model"
 mname_orig = "xlm-roberta-base"
 mname_tiny = "tiny-xlm-roberta"
 ### Tokenizer
 # Shrink the orig vocab to keep things small
 vocab_keep_items = 5000
+tmp_dir = f"/tmp/{mname_tiny}"
 vocab_orig_path = f"{tmp_dir}/sentencepiece.bpe.model"
 vocab_short_path = f"{tmp_dir}/spiece-short.model"
 if 1: # set to 0 to skip this after running once to speed things up during tune up
 readme = "README.md"
 if not os.path.exists(readme):
     with open(readme, "w") as f:
+        f.write(f"This is a {mname_tiny} random model to be used for basic testing.\n")
 print(f"Generated {mname_tiny}")