nvidia
/

Llama-3_1-Nemotron-Ultra-253B-v1

Text Generation

Model card Files Files and versions Community

jiaqiz commited on 22 days ago

Commit

db3ffa0

·

verified ·

1 Parent(s): a44faee

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/lustre/fs1/portfolios/llmservice/users/soumyes/llama-nemotron/results/cw_smy_253b_sft_sp_ultra_blend_v1_maxlen_24k_shuffled_lr8e-6_minlr8e-7_warmup800_GBS256_rerun-step-5700/checkpoints/HF/step1800",
   "architectures": [
     "DeciLMForCausalLM"
   ],

 {
+  "_name_or_path": "llama_nemotron_ultra",
   "architectures": [
     "DeciLMForCausalLM"
   ],