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
12
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

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

Base model

google/gemma-2-9b
Finetuned
(227)
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