neuralmagic
/

Meta-Llama-3.1-8B-Instruct-FP8-dynamic

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

Lin-K76 commited on Jul 23, 2024

Commit

8006c32

·

verified ·

1 Parent(s): 223e6f5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -105,7 +105,7 @@ quant_stage:
                     targets: ["Linear"]
 """
-model_stub = "/meta-llama/Meta-Llama-3.1-8B-Instruct"
 model_name = model_stub.split("/")[-1]
 device_map = calculate_offload_device_map(

                     targets: ["Linear"]
 """
+model_stub = "meta-llama/Meta-Llama-3.1-8B-Instruct"
 model_name = model_stub.split("/")[-1]
 device_map = calculate_offload_device_map(