meta-llama/Llama-3.2-3B-Instruct - W4A16 Compression

This is a compressed model using llmcompressor.

Compression Configuration

  • Base Model: meta-llama/Llama-3.2-3B-Instruct
  • Compression Scheme: W4A16
  • Dataset: HuggingFaceH4/ultrachat_200k
  • Dataset Split: train_sft
  • Number of Samples: 512
  • Preprocessor: chat
  • Maximum Sequence Length: 131072

Sample Output

Prompt:

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

Cutting Knowledge Date: December 2023
Today Date: 28 Nov 2024

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

Who is Alan Turing?<|eot_id|>

Output:

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

Cutting Knowledge Date: December 2023
Today Date: 28 Nov 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 the development of computer science, artificial intelligence, and cryptography. He is widely considered one of the most influential figures in the history of computer science.

Early Life and Education:

Turing was born in London, England, on June 23, 1912. He was educated at King's School in Croton, and later at King's College, Cambridge, where he studied mathematics and philosophy. During World War II, Turing worked at the Government Code and Cypher School (GC

Evaluation

Downloads last month
40
Safetensors
Model size
1.16B params
Tensor type
I64
·
I32
·
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 espressor/meta-llama.Llama-3.2-3B-Instruct_W4A16

Quantized
(195)
this model

Dataset used to train espressor/meta-llama.Llama-3.2-3B-Instruct_W4A16