Text Generation
Transformers
Safetensors
llama
sparse
code
text-generation-inference
Inference Endpoints
Edit model card

Llama-2-7b-pruned50-retrained-evolcodealpaca

This repo contains a 50% 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-pruned50-retrained-evolcodealpaca")
model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned50-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-pruned50-retrained-evolcodealpaca
HumanEval pass@1 32.03 38.15

Model Training Details

This model was obtained by sparse-tranfer of the sparse foundational model Llama-2-7b-pruned50-retrained on 60% of the evolcodealpaca dataset. Training was perfomerd for 2 epochs and used the SquareHead knowledge distillation with Llama-2-7b-evolcodealpaca as teacher.

Help

For further support, and discussions on these models and AI in general, join Neural Magic's Slack Community

Downloads last month
19
Safetensors
Model size
6.74B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for neuralmagic/Llama-2-7b-evol-code-alpaca-pruned_50

Finetuned
(5)
this model
Quantizations
1 model

Datasets used to train neuralmagic/Llama-2-7b-evol-code-alpaca-pruned_50

Collection including neuralmagic/Llama-2-7b-evol-code-alpaca-pruned_50