Instructions to use abacaj/phi-2-super with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacaj/phi-2-super with Transformers:

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

pipe = pipeline("text-generation", model="abacaj/phi-2-super", 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("abacaj/phi-2-super", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("abacaj/phi-2-super", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abacaj/phi-2-super with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacaj/phi-2-super"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacaj/phi-2-super",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abacaj/phi-2-super

SGLang

How to use abacaj/phi-2-super 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 "abacaj/phi-2-super" \
    --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": "abacaj/phi-2-super",
		"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 "abacaj/phi-2-super" \
        --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": "abacaj/phi-2-super",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abacaj/phi-2-super with Docker Model Runner:
```
docker model run hf.co/abacaj/phi-2-super
```

abacaj

lewtun HF Staff commited on Mar 2, 2024

Commit

2d6482f

verified ·

1 Parent(s): f1e578c

Add IFEval score to metrics (#2)

Browse files

- Add IFEval score to metrics (b4bbb89cdfec15934d34e79103b7a4ccb4e43127)

Co-authored-by: Lewis Tunstall <lewtun@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +17 -0

README.md CHANGED Viewed

@@ -14,6 +14,23 @@ tags:
 - convAI
 - conversational
 pipeline_tag: text-generation
 ---
 # Phi-2-super (SFT + cDPO)

 - convAI
 - conversational
 pipeline_tag: text-generation
+model-index:
+- name: phi-2-super
+  results:
+  # IFEval
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Instruction Following Eval
+      type: wis-k/instruction-following-eval
+    metrics:
+       - type: acc
+         name: prompt_level_loose_acc
+         value: 0.2717
+    source:
+      name: LightEval
+      url: https://github.com/huggingface/lighteval
 ---
 # Phi-2-super (SFT + cDPO)