google/gemma-2-9b - 2b_2n4m_128bs Compression

This is a compressed model using deltazip.

Paper, Compression Tool, Inference Engine (Soon).

Compression Configuration

  • Base Model: google/gemma-2-9b
  • 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:

<bos><start_of_turn>user
Who is Alan Turing?<end_of_turn>
*Alan Turing* (1912-1954) was a British mathematician and computer scientist who is considered one of the founding fathers of theoretical computer science and artificial intelligence. 

Here are some key points about his life and work:

**Early Life and Education:**

* Born in London, England, in 1912.
* Showed exceptional mathematical talent from a young age.
* Studied mathematics at King's College, Cambridge.

**World War II Contributions:**

* During World War II, Turing worked at Bletchley

Evaluation

Downloads last month
3
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for deltazip/google.gemma-2-9b-it.2b_2n4m_128bs

Base model

google/gemma-2-9b
Finetuned
(225)
this model

Dataset used to train deltazip/google.gemma-2-9b-it.2b_2n4m_128bs

Collection including deltazip/google.gemma-2-9b-it.2b_2n4m_128bs