Instructions to use saurabhapd/phi3-4k-it-nvidia-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saurabhapd/phi3-4k-it-nvidia-chat with Transformers:

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

pipe = pipeline("text-generation", model="saurabhapd/phi3-4k-it-nvidia-chat", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("saurabhapd/phi3-4k-it-nvidia-chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("saurabhapd/phi3-4k-it-nvidia-chat", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use saurabhapd/phi3-4k-it-nvidia-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saurabhapd/phi3-4k-it-nvidia-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saurabhapd/phi3-4k-it-nvidia-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saurabhapd/phi3-4k-it-nvidia-chat

SGLang

How to use saurabhapd/phi3-4k-it-nvidia-chat 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 "saurabhapd/phi3-4k-it-nvidia-chat" \
    --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": "saurabhapd/phi3-4k-it-nvidia-chat",
		"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 "saurabhapd/phi3-4k-it-nvidia-chat" \
        --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": "saurabhapd/phi3-4k-it-nvidia-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use saurabhapd/phi3-4k-it-nvidia-chat with Docker Model Runner:
```
docker model run hf.co/saurabhapd/phi3-4k-it-nvidia-chat
```

saurabhapd commited on May 15, 2024

Commit

51058fb

verified ·

1 Parent(s): dacc196

Upload Phi3ForCausalLM

Browse files

Files changed (3) hide show

model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113115f3775da2df07e229d5ef12f16e742a6743eafa3d1d975628a3c4583a4a
 size 4961852416

 version https://git-lfs.github.com/spec/v1
+oid sha256:f858ee0bcb4aa4716805264d4837ae774d6d0d9cae399172acaf8c99fc7cb129
 size 4961852416

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3711399916fdef53058131683d3599ba95bbd1aa42e44db5ac036b643633ec
 size 4983111176

 version https://git-lfs.github.com/spec/v1
+oid sha256:6bd03b73633c575972a47bb439bce403efd92bfa8b949c5ac0a515e27fdaa1c8
 size 4983111176

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ad57f2eac0c7bb2dd7ac88d8e7c6c7474e80c2063558a9d5c2b7ee7ca8b1b9
 size 4945374704

 version https://git-lfs.github.com/spec/v1
+oid sha256:cbb3542943c633ae0dc78f78234ff5154de190a55c8dade21d47eb11ba745fe5
 size 4945374704