Instructions to use huggingtweets/scottmorrisonmp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huggingtweets/scottmorrisonmp with Transformers:

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

pipe = pipeline("text-generation", model="huggingtweets/scottmorrisonmp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingtweets/scottmorrisonmp")
model = AutoModelForCausalLM.from_pretrained("huggingtweets/scottmorrisonmp")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huggingtweets/scottmorrisonmp with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/scottmorrisonmp

SGLang

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

Docker Model Runner
How to use huggingtweets/scottmorrisonmp with Docker Model Runner:
```
docker model run hf.co/huggingtweets/scottmorrisonmp
```

boris commited on Feb 1, 2022

Commit

4e94b3c

1 Parent(s): 1989903

New model from https://wandb.ai/wandb/huggingtweets/runs/19568gcc

Browse files

Files changed (3) hide show

README.md +3 -3
pytorch_model.bin +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -47,15 +47,15 @@ The model was trained on tweets from Scott Morrison.
 | Short tweets | 34 |
 | Tweets kept | 2599 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/25hd5hto/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @scottmorrisonmp's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/33seglt4) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/33seglt4/artifacts) is logged and versioned.
 ## How to use

 | Short tweets | 34 |
 | Tweets kept | 2599 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1ytdoprx/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @scottmorrisonmp's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/19568gcc) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/19568gcc/artifacts) is logged and versioned.
 ## How to use

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e68a63284139a2df9fccff188476abb038b3a2428546b6db412697a5bd49461
 size 510403817

 version https://git-lfs.github.com/spec/v1
+oid sha256:434a906855d8547d7d05a39c8612393b6cf374314b29c6147e8431f2aa765462
 size 510403817

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058acab903cb1c62b758f771dd10f6fab649ab0f4f11ae063414afc89b62a4ad
 size 3055

 version https://git-lfs.github.com/spec/v1
+oid sha256:e46632de2fe7c9d80748dec62b485871467f41d5c5cce5db4953a1c45431bcca
 size 3055