Fix : model used to test ggml conversion of Falcon-7b is incorrect (#… #409

Job	Run time
Model CI / Check Runner Status	6s
Example CI / Check Runner Status	8s
Torch pipeline CI / Check Runner Status	8s
DeepSpeed CI / Check Runner Status	5s
Model CI / Check Runners (single-gpu)	1s
Model CI / Check Runners (multi-gpu)	1s
DeepSpeed CI / Check Runners (single-gpu)	1s
DeepSpeed CI / Check Runners (multi-gpu)	1s
Torch pipeline CI / Check Runners (single-gpu)	1s
Torch pipeline CI / Check Runners (multi-gpu)	1s
Example CI / Check Runners (single-gpu)	1s
Example CI / Check Runners (multi-gpu)	1s
Model CI / Examples directory	1s
Model CI / PyTorch pipelines	1s
Model CI / Setup	1s
Model CI / Torch ROCm deepspeed tests	1s
DeepSpeed CI / Examples directory	1s
DeepSpeed CI / PyTorch pipelines	1s
DeepSpeed CI / Setup	1s
DeepSpeed CI / Torch ROCm deepspeed tests	1s
Torch pipeline CI / Examples directory	1s
Torch pipeline CI / PyTorch pipelines	1s
Torch pipeline CI / Setup	1s
Torch pipeline CI / Torch ROCm deepspeed tests	1s
Example CI / PyTorch pipelines	1s
Example CI / Setup	1s
Example CI / Examples directory	1s
Example CI / Torch ROCm deepspeed tests	1s
Model CI / Single GPU tests	1s
DeepSpeed CI / Single GPU tests	1s
Torch pipeline CI / Single GPU tests	1s
Example CI / Single GPU tests	1s
Model CI / Slack Report / Send results to webhook	16s
DeepSpeed CI / Slack Report / Send results to webhook	18s
Torch pipeline CI / Slack Report / Send results to webhook	15s
Example CI / Slack Report / Send results to webhook	15s
	1m 59s

Provide feedback