meta-llama/Llama-3.1-8B - 2b_2n4m_128bs Compression

This is a compressed model using deltazip.

Paper, Compression Tool, Inference Engine (Soon).

Compression Configuration

  • Base Model: meta-llama/Llama-3.1-8B
  • Compression Scheme: 2b_2n4m_128bs
  • Dataset: HuggingFaceH4/ultrachat_200k
  • Dataset Split: train_sft
  • Max Sequence Length: 2048
  • Number of Samples: 256

Sample Output

Prompt:

[{'role': 'user', 'content': 'Who is Alan Turing?'}]

Output:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Cutting Knowledge Date: December 2023
Today Date: 26 Jul 2024

<|eot_id|><|start_header_id|>user<|end_header_id|>

Who is Alan Turing?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Alan Turing (1912-1954) was a British mathematician, computer scientist, logician, and philosopher who made significant contributions to various fields, including computer science, artificial intelligence, and cryptography. He is widely considered one of the most influential figures in the development of modern computer science.

**Early Life and Education**

Alan Turing was born on June 23, 1912, in London, England. He showed a talent for

Evaluation

Downloads last month
2
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for deltazip/meta-llama.Llama-3.1-8B-Instruct.2b_2n4m_128bs

Finetuned
(708)
this model

Dataset used to train deltazip/meta-llama.Llama-3.1-8B-Instruct.2b_2n4m_128bs

Collection including deltazip/meta-llama.Llama-3.1-8B-Instruct.2b_2n4m_128bs