nvidia
/

Nemotron-H-4B-Base-8K

Text Generation

Model card Files Files and versions

suhara commited on Apr 12, 2025

Commit

8f26a60

·

verified ·

1 Parent(s): eb78bd0

Update config.json

Files changed (1) hide show

config.json +4 -4

config.json CHANGED Viewed

@@ -1,13 +1,13 @@
 {
   "architectures": [
-    "Nemotron5ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
    "attention_head_dim": 128,
   "auto_map": {
-    "AutoConfig": "configuration_nemotron5.Nemotron5Config",
-    "AutoModelForCausalLM": "modeling_nemotron5.Nemotron5ForCausalLM"
   },
   "bos_token_id": 1,
   "chunk_size": 256,
@@ -27,7 +27,7 @@
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "mlp_hidden_act": "relu2",
-  "model_type": "nemotron5",
   "n_groups": 8,
   "num_attention_heads": 32,
   "num_hidden_layers": 52,

 {
   "architectures": [
+    "NemotronHForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
    "attention_head_dim": 128,
   "auto_map": {
+    "AutoConfig": "configuration_nemotron_h.NemotronHConfig",
+    "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
   },
   "bos_token_id": 1,
   "chunk_size": 256,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "mlp_hidden_act": "relu2",
+  "model_type": "nemotron_h",
   "n_groups": 8,
   "num_attention_heads": 32,
   "num_hidden_layers": 52,