Instructions to use ondevicellm/phi-1_5_sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ondevicellm/phi-1_5_sft with Transformers:

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

pipe = pipeline("text-generation", model="ondevicellm/phi-1_5_sft", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("ondevicellm/phi-1_5_sft", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ondevicellm/phi-1_5_sft", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ondevicellm/phi-1_5_sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ondevicellm/phi-1_5_sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ondevicellm/phi-1_5_sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ondevicellm/phi-1_5_sft

SGLang

How to use ondevicellm/phi-1_5_sft 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 "ondevicellm/phi-1_5_sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ondevicellm/phi-1_5_sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ondevicellm/phi-1_5_sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ondevicellm/phi-1_5_sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ondevicellm/phi-1_5_sft with Docker Model Runner:
```
docker model run hf.co/ondevicellm/phi-1_5_sft
```

hushell commited on Feb 27, 2024

Commit

2cdfa33

verified ·

1 Parent(s): 2fb7c16

Training in progress, step 800

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Feb27_20-52-50_main1/events.out.tfevents.1709068444.main1.69011.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea4bb9a4c488cd63c2f109d0f873c4a11b69edd39bf4d0b309a8647c56d91fc
 size 2836579040

 version https://git-lfs.github.com/spec/v1
+oid sha256:49625bb1a469eb4e9e3cddbb3fb91042f321786f439266e22bae785f1752699e
 size 2836579040

runs/Feb27_20-52-50_main1/events.out.tfevents.1709068444.main1.69011.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327d6c4e39b0b9b902ffd35ae1285349824f1b2dad734f244312b51a51b10628
-size 28631

 version https://git-lfs.github.com/spec/v1
+oid sha256:f0121d9362957ae1c32ae360a753899bf96291bdbd22c88869d6dc57239e61fc
+size 32042