meta-llama/Llama-2-7b-chat-hf - W8A8_FP8 Compression

This is a compressed model using llmcompressor.

Compression Configuration

  • Base Model: meta-llama/Llama-2-7b-chat-hf
  • Compression Scheme: W8A8_FP8
  • Dataset: HuggingFaceH4/ultrachat_200k
  • Dataset Split: train_sft
  • Number of Samples: 512
  • Preprocessor: chat
  • Maximum Sequence Length: 4096

Sample Output

Prompt:

<s>[INST] Who is Alan Turing? [/INST]

Output:

<s><s> [INST] Who is Alan Turing? [/INST]  Alan Turing (1912-1954) was a British mathematician, computer scientist, and codebreaker who made significant contributions to the fields of computer science, artificial intelligence, and cryptography.

Turing is widely considered to be the father of computer science and artificial intelligence. He proposed the Turing machine, a theoretical model for a computer that is still used today as a basis for understanding the fundamental principles of computation. He also developed the concept of the universal Turing machine, which is a more powerful model of a computer that can simulate the behavior of any other computer.

Evaluation

Downloads last month
27
Safetensors
Model size
6.74B params
Tensor type
FP16
·
F8_E4M3
·
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-2-7b-chat-hf_W8A8_FP8

Quantized
(61)
this model

Dataset used to train espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_FP8