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

Libraries

How to use SteelStorage/phi-2-DLEC with Transformers:

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

pipe = pipeline("text-generation", model="SteelStorage/phi-2-DLEC", 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("SteelStorage/phi-2-DLEC", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("SteelStorage/phi-2-DLEC", 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 SteelStorage/phi-2-DLEC with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SteelStorage/phi-2-DLEC

SGLang

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

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

Steelskull commited on Mar 21, 2024

Commit

87ffdfd

verified ·

1 Parent(s): 409f695

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -5

README.md CHANGED Viewed

@@ -58,14 +58,17 @@ Currently, I am still limited to Mergekit, for this method, which does not suppo
 ## ⚙️ Evals
-My Leaderboard:
-https://huggingface.co/spaces/Steelskull/YALL-Leaderboard
 As you know there is a usual loss of intelligence with model mergers, especially with Passthrough merging, on the par of 3ish points per billion duped, IF you get the right merge, if not your looking at a much larger loss (anywhere from 3-8 points per billion duped).
-With DLEC, I was able to increase Phi-2 from 2.78b -> 3.25b with less than or equal to a single point of loss.
-This method is still in active development, and T am currently tweaking the algorithm to improve the layer selection process,
-I am also working on a single layer duping script as merge kit does not currently support this and I am being forced to merge layers that are unneeded and its degrading performance.
 ## 🧩 Configuration

 ## ⚙️ Evals
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/pS7KFYDheWmFEaGybxr3K.png)
+[My Leaderboard:](https://huggingface.co/spaces/Steelskull/YALL-Leaderboard)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/CF9_p8AWMFraCnfiMa_no.png)
 As you know there is a usual loss of intelligence with model mergers, especially with Passthrough merging, on the par of 3ish points per billion duped, IF you get the right merge, if not your looking at a much larger loss (anywhere from 3-8 points per billion duped).
+Using DLEC, I was able to increase Phi-2 from 2.78b -> 3.25b with less than or around a single point of loss.
+This method is still in active development, and I am currently tweaking the algorithm to improve the layer selection process,
+I am also working on a single layer duping script as merge kit does not currently support this and I am merging layers that are unneeded and its degrading performance.
 ## 🧩 Configuration