meta-llama/Llama-2-70b-chat-hf - W8A8_FP8 Compression

This is a compressed model using llmcompressor.

Compression Configuration

Base Model: meta-llama/Llama-2-70b-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:

Could not generate output

Output:

No CUDA GPUs are available

Evaluation

Downloads last month: 30

Safetensors

Model size

69B params

Tensor type

FP16

F8_E4M3

Inference Examples

Text Generation

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-2-70b-chat-hf_W8A8_FP8

Base model

meta-llama/Llama-2-70b-chat-hf

Quantized

(9)

this model

espressor
/

meta-llama.Llama-2-70b-chat-hf_W8A8_FP8