allenai
/

Olmo-3-7B-RL-Zero-IF

Text Generation

Model card Files Files and versions

saurabh5 commited on 19 days ago

Commit

b3502c4

·

verified ·

1 Parent(s): 69d440c

Update config.json on branch main

Files changed (1) hide show

config.json +6 -5

config.json CHANGED Viewed

@@ -1,9 +1,10 @@
 {
   "architectures": [
-    "Olmo2RetrofitForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "eos_token_id": 100257,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -44,7 +45,7 @@
     "full_attention"
   ],
   "max_position_embeddings": 65536,
-  "model_type": "olmo2-retrofit",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
@@ -61,8 +62,8 @@
   "rope_theta": 500000,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.54.0.dev0",
-  "use_cache": false,
   "vocab_size": 100278
 }

 {
   "architectures": [
+    "Olmo3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "dtype": "bfloat16",
   "eos_token_id": 100257,
   "hidden_act": "silu",
   "hidden_size": 4096,
     "full_attention"
   ],
   "max_position_embeddings": 65536,
+  "model_type": "olmo3",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "rope_theta": 500000,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
   "vocab_size": 100278
 }