Downloads · 30 days
11
3% of all-time downloads
yang31210999/Llama3.1-1B-Neo-BAAI-1000k
Llama3.1-1B-Neo-BAAI-1000k is a text generation model from yang31210999. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
We prune the Llama-3.1-8B-Instruct to 1.4B and fine-tune it with LLM-Neo method,which combines LoRA and KD in one. Training data is sampling from BAAI/Infinity-Instruct for 1 Million lines.
Downloads · 30 days
11
3% of all-time downloads
All-time downloads
411
Public
Parameters
1.9B
7.7 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors7.7 GB · 100%
From the Hugging Face model README
We prune the Llama-3.1-8B-Instruct to 1.4B and fine-tune it with LLM-Neo method,which combines LoRA and KD in one. Training data is sampling from BAAI/Infinity-Instruct for 1 Million lines.
For more information, please refer to the paper: LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models
Code can be found here: https://github.com/yang3121099/LLM-Neo
In this section, we report the results for Llama3.1-Neo-1B-100w on standard automatic benchmarks. For all the evaluations, we use lm-evaluation-harness library.