Instructions to use RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70

SGLang

How to use RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70 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 "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-2-7b-pruned70-retrained-evolcodealpaca

This repo contains a 70% sparse Llama 2 7B finetuned for code generation tasks using the Evolved CodeAlpaca dataset.

Official model weights from Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment.

Authors: Neural Magic, Cerebras

Usage

Below we share some code snippets on how to get quickly started with running the model.

Sparse Transfer

By leveraging a pre-sparsified model's structure, you can efficiently fine-tune on new data, leading to reduced hyperparameter tuning, training times, and computational costs. Learn about this process here.

Running the model

This model may be run with the transformers library. For accelerated inference with sparsity, deploy with nm-vllm or deepsparse.

# pip install transformers accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained-evolcodealpaca")
model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained-evolcodealpaca", device_map="auto")

input_text = "def fibonacci(n):\n"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

Evaluation Benchmark Results

Model evaluation metrics and results.

Benchmark	Metric	Llama-2-7b-evolcodealpaca	Llama-2-7b-pruned70-retrained-evolcodealpaca
HumanEval	pass@1	32.03	36.3

Model Training Details

This model was obtained by gradual sparse-transfer of the sparse foundational model Llama-2-7b-pruned50-retrained on 60% of the evolcodealpaca dataset. The 50% sparse foundational model was finetuned for 2 epochs and then pruned to 70% sparsity using SparseGPT. Then, the model was finetuned for 1 more epoch with the SquareHead knowledge distillation with Llama-2-7b-evolcodealpaca as teacher.