Instructions to use ManuelPerdigo/OPT-350_mlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ManuelPerdigo/OPT-350_mlm with Transformers:

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

pipe = pipeline("text-generation", model="ManuelPerdigo/OPT-350_mlm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ManuelPerdigo/OPT-350_mlm")
model = AutoModelForCausalLM.from_pretrained("ManuelPerdigo/OPT-350_mlm")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ManuelPerdigo/OPT-350_mlm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ManuelPerdigo/OPT-350_mlm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ManuelPerdigo/OPT-350_mlm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ManuelPerdigo/OPT-350_mlm

SGLang

How to use ManuelPerdigo/OPT-350_mlm 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 "ManuelPerdigo/OPT-350_mlm" \
    --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": "ManuelPerdigo/OPT-350_mlm",
		"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 "ManuelPerdigo/OPT-350_mlm" \
        --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": "ManuelPerdigo/OPT-350_mlm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ManuelPerdigo/OPT-350_mlm with Docker Model Runner:
```
docker model run hf.co/ManuelPerdigo/OPT-350_mlm
```

ManuelPerdigo commited on Jul 25, 2023

Commit

1a111dd

1 Parent(s): 253d61d

End of training

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Jul25_00-29-34_c30446c757cf/events.out.tfevents.1690244977.c30446c757cf.248.3 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8405e878af30431bdc5220b2b458bfd4cd5c42cb2f2efec84c84c2c5bd3a8a77
 size 1324917277

 version https://git-lfs.github.com/spec/v1
+oid sha256:fb3da7c6a69a7e6339e98626f3c5e1dce01ca09716c91a28ffbc7d347bf3a307
 size 1324917277

runs/Jul25_00-29-34_c30446c757cf/events.out.tfevents.1690244977.c30446c757cf.248.3 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1642097f0d162f751850d0d3091034dda937dddffac85be04f25efa1a57be62
-size 5648

 version https://git-lfs.github.com/spec/v1
+oid sha256:7d1648063fc390cce86a5472c25464bfca29f6bd14acd039460febf3726bdf08
+size 6273