meta-llama/Meta-Llama-3-8B-Instruct - W4A16 Compression

This is a compressed model using llmcompressor.

Compression Configuration

  • Base Model: meta-llama/Meta-Llama-3-8B-Instruct
  • Compression Scheme: W4A16
  • Dataset: HuggingFaceH4/ultrachat_200k
  • Dataset Split: train_sft
  • Number of Samples: 512
  • Preprocessor: chat
  • Maximum Sequence Length: 8192

Sample Output

Prompt:

<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Who is Alan Turing?<|eot_id|>

Output:

<|begin_of_text|><|begin_of_text|><|start_header_id|>user<|end_header_id|>

Who is Alan Turing?<|eot_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|>

Evaluation

Downloads last month
4
Safetensors
Model size
1.98B params
Tensor type
BF16
·
I64
·
I32
·
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.Meta-Llama-3-8B-Instruct_W4A16

Quantized
(186)
this model

Dataset used to train espressor/meta-llama.Meta-Llama-3-8B-Instruct_W4A16