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

Libraries

How to use huggingtweets/italyhightech with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingtweets/italyhightech")
model = AutoModelForCausalLM.from_pretrained("huggingtweets/italyhightech", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/italyhightech with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/italyhightech

SGLang

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

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

boris commited on Apr 22, 2023

Commit

ed58e44

1 Parent(s): cf454f6

New model from https://wandb.ai/wandb/huggingtweets/runs/216554da

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 Valentino Zocca 🇮🇹 🇪🇺 👍.
 | Short tweets | 91 |
 | Tweets kept | 1552 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/mwke7gz8/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 @italyhightech's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/j0qjdje6) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/j0qjdje6/artifacts) is logged and versioned.
 ## How to use

 | Short tweets | 91 |
 | Tweets kept | 1552 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/nawyyij5/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 @italyhightech's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/216554da) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/216554da/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 sha256:623ad8722d1e8fd5f165dc063ab7f77b8810e6f3e09b34872d4a9bde09d9d22e
 size 510398013

 version https://git-lfs.github.com/spec/v1
+oid sha256:c8479eb38d65dde3ebe84834982fe2ed96a3de38eab2b3a9f8e71db21415fdcc
 size 510398013

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8dec9784387aa3dc3faf5046d6633d3b28c50de820bacaefac64be3713f1f50
 size 3579

 version https://git-lfs.github.com/spec/v1
+oid sha256:7ea62b87763bf9058f0aed964d385bd3a9e3e570c4b0d0204cd399471c941bb6
 size 3579