meta-llama/Llama-3.1-8B-Instruct - W8A8_int8 Compression

This is a compressed model using llmcompressor.

Compression Configuration

  • Base Model: meta-llama/Llama-3.1-8B-Instruct
  • Compression Scheme: W8A8_int8
  • 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: 26 Jul 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: 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 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 showed a talent for mathematics and logic from an early age and was accepted into King's College, Cambridge, where he studied mathematics. During his time at Cambridge, he was elected a scholar of King's College and

Evaluation

Downloads last month
7
Safetensors
Model size
8.03B params
Tensor type
BF16
·
I8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8

Quantized
(410)
this model

Dataset used to train espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8