Instructions to use Realluke/phi-2-senator-tweets with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Realluke/phi-2-senator-tweets with Transformers:

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

pipe = pipeline("text-generation", model="Realluke/phi-2-senator-tweets", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Realluke/phi-2-senator-tweets", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Realluke/phi-2-senator-tweets", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Realluke/phi-2-senator-tweets with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Realluke/phi-2-senator-tweets"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Realluke/phi-2-senator-tweets",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Realluke/phi-2-senator-tweets

SGLang

How to use Realluke/phi-2-senator-tweets 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 "Realluke/phi-2-senator-tweets" \
    --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": "Realluke/phi-2-senator-tweets",
		"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 "Realluke/phi-2-senator-tweets" \
        --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": "Realluke/phi-2-senator-tweets",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Realluke/phi-2-senator-tweets with Docker Model Runner:
```
docker model run hf.co/Realluke/phi-2-senator-tweets
```

Phi-2 Senator Tweets

Phi-2 finetuned on Senator Tweets.

The starting token is [start] and the ending token is [end]

Example:

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("Realluke/phi-2-senator-tweets", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)

inputs = tokenizer("[start]", return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]

print(text)

Model Details

Model Description

Steps: 750
Finetuning Examples: 1000
GPU: NVIDIA Tesla T4
GPU Hours: 2

Downloads last month: 14

Safetensors

Model size

3B params

Tensor type

F16

Realluke
/

phi-2-senator-tweets

Phi-2 Senator Tweets

Model Details

Model Description

Dataset used to train Realluke/phi-2-senator-tweets