Instructions to use NobodyExistsOnTheInternet/phi2v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NobodyExistsOnTheInternet/phi2v2 with Transformers:

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

pipe = pipeline("text-generation", model="NobodyExistsOnTheInternet/phi2v2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("NobodyExistsOnTheInternet/phi2v2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NobodyExistsOnTheInternet/phi2v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NobodyExistsOnTheInternet/phi2v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NobodyExistsOnTheInternet/phi2v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NobodyExistsOnTheInternet/phi2v2

SGLang

How to use NobodyExistsOnTheInternet/phi2v2 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 "NobodyExistsOnTheInternet/phi2v2" \
    --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": "NobodyExistsOnTheInternet/phi2v2",
		"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 "NobodyExistsOnTheInternet/phi2v2" \
        --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": "NobodyExistsOnTheInternet/phi2v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NobodyExistsOnTheInternet/phi2v2 with Docker Model Runner:
```
docker model run hf.co/NobodyExistsOnTheInternet/phi2v2
```

NobodyExistsOnTheInternet commited on Nov 20, 2023

Commit

8e2788a

1 Parent(s): a2f1254

Delete MLmodel

Browse files

Files changed (1) hide show

MLmodel +0 -24

MLmodel DELETED Viewed

@@ -1,24 +0,0 @@
-flavors:
-  hftransformersv2:
-    code: null
-    config_hf_load_kwargs:
-      trust_remote_code: true
-    hf_config_class: AutoConfig
-    hf_pretrained_class: AutoModelForCausalLM
-    hf_tokenizer_class: CodeGenTokenizerFast
-    model_data: data
-    model_hf_load_args:
-      trust_remote_code: true
-    pytorch_version: 2.1.0+cu118
-    task_type: text-generation
-    tokenizer_hf_load_kwargs:
-      trust_remote_code: true
-    transformers_version: 4.34.0
-  python_function:
-    data: data
-    env: conda.yaml
-    loader_module: azureml.evaluate.mlflow.hftransformers
-    python_version: 3.10.11
-mlflow_version: 2.6.0
-model_uuid: 6068cffa9b034ea28c997f4538233299
-utc_time_created: '2023-11-06 18:18:55.524636'