Text Generation
Transformers
Safetensors
phi
mergekit
Merge
custom_code
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use Shaleen123/phi-2-merge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shaleen123/phi-2-merge with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Shaleen123/phi-2-merge", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Shaleen123/phi-2-merge", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Shaleen123/phi-2-merge", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Shaleen123/phi-2-merge with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Shaleen123/phi-2-merge" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Shaleen123/phi-2-merge", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Shaleen123/phi-2-merge
- SGLang
How to use Shaleen123/phi-2-merge 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 "Shaleen123/phi-2-merge" \ --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": "Shaleen123/phi-2-merge", "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 "Shaleen123/phi-2-merge" \ --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": "Shaleen123/phi-2-merge", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Shaleen123/phi-2-merge with Docker Model Runner:
docker model run hf.co/Shaleen123/phi-2-merge
Download tests/test_modelref.py from Shaleen123/phi-2-merge: direct link, hf CLI and curl.
- Browser
- Download file 1.5 kB
-
https://huggingface.co/Shaleen123/phi-2-merge/resolve/main/tests/test_modelref.py
- Command line
-
hf download hf://Shaleen123/phi-2-merge/tests/test_modelref.py
-
curl -L -o test_modelref.py https://huggingface.co/Shaleen123/phi-2-merge/resolve/main/tests/test_modelref.py
1.5 kB
| import pytest | |
| from mergekit.common import ModelPath, ModelReference | |
| class TestModelReference: | |
| def test_parse_simple(self): | |
| text = "hf_user/model" | |
| mr = ModelReference.parse(text) | |
| assert mr.model == ModelPath(path="hf_user/model", revision=None) | |
| assert mr.lora is None | |
| assert str(mr) == text | |
| def test_parse_lora(self): | |
| text = "hf_user/model+hf_user/lora" | |
| mr = ModelReference.parse(text) | |
| assert mr.model == ModelPath(path="hf_user/model", revision=None) | |
| assert mr.lora == ModelPath(path="hf_user/lora", revision=None) | |
| assert str(mr) == text | |
| def test_parse_revision(self): | |
| text = "hf_user/model@v0.0.1" | |
| mr = ModelReference.parse(text) | |
| assert mr.model == ModelPath(path="hf_user/model", revision="v0.0.1") | |
| assert mr.lora is None | |
| assert str(mr) == text | |
| def test_parse_lora_plus_revision(self): | |
| text = "hf_user/model@v0.0.1+hf_user/lora@main" | |
| mr = ModelReference.parse(text) | |
| assert mr.model == ModelPath(path="hf_user/model", revision="v0.0.1") | |
| assert mr.lora == ModelPath(path="hf_user/lora", revision="main") | |
| assert str(mr) == text | |
| def test_parse_bad(self): | |
| with pytest.raises(RuntimeError): | |
| ModelReference.parse("@@@@@") | |
| with pytest.raises(RuntimeError): | |
| ModelReference.parse("a+b+c") | |
| with pytest.raises(RuntimeError): | |
| ModelReference.parse("a+b+c@d+e@f@g") | |