DanielTanasescu
/

raw-250m

Text Generation

foundation-model

random-initialization

Model card Files Files and versions

raw-250m / runtime.yaml

T.D.

Upload 14 files

9f99823 verified 16 days ago

History Blame Contribute Delete

149 Bytes

	precision: bfloat16
	context_length: 4096
	attention: flash/sdpa causal
	kv_cache_dtype: bf16
	rope_theta: 500000.0
	architecture: LlamaForCausalLM