Instructions to use OEvortex/EMO-phi-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OEvortex/EMO-phi-128k with Transformers:

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

pipe = pipeline("text-generation", model="OEvortex/EMO-phi-128k", 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("OEvortex/EMO-phi-128k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OEvortex/EMO-phi-128k", trust_remote_code=True)
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 OEvortex/EMO-phi-128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OEvortex/EMO-phi-128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OEvortex/EMO-phi-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OEvortex/EMO-phi-128k

SGLang

How to use OEvortex/EMO-phi-128k 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 "OEvortex/EMO-phi-128k" \
    --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": "OEvortex/EMO-phi-128k",
		"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 "OEvortex/EMO-phi-128k" \
        --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": "OEvortex/EMO-phi-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OEvortex/EMO-phi-128k with Docker Model Runner:
```
docker model run hf.co/OEvortex/EMO-phi-128k
```

Abhaykoul commited on Apr 24, 2024

Commit

3cb7b87

verified ·

1 Parent(s): d942fc6

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -53,7 +53,7 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype="auto",
     trust_remote_code=True,
 )
-tokenizer = AutoTokenizer.from_pretrained("OEvortex/EMO-phi-128k")
 messages = [
     {"role": "system", "content": "You are a helpful Emotional intelligence named as EMO-phi, remember to always answer users question in EMO style."},
@@ -67,7 +67,7 @@ pipe = pipeline(
 )
 generation_args = {
-    "max_new_tokens": 2024,
     "return_full_text": False,
     "temperature": 0.6,
     "do_sample": True,

     torch_dtype="auto",
     trust_remote_code=True,
 )
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
 messages = [
     {"role": "system", "content": "You are a helpful Emotional intelligence named as EMO-phi, remember to always answer users question in EMO style."},
 )
 generation_args = {
+    "max_new_tokens": 500,
     "return_full_text": False,
     "temperature": 0.6,
     "do_sample": True,