AdinaM
/

hackathon_datacrowd

Mixture of Experts

Eval Results (legacy)

text-generation-inference

Model card Files Files and versions

AdinaM commited on Apr 19, 2024

Commit

9731c8c

·

verified ·

1 Parent(s): 77fc1f2

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -10,7 +10,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 16384,
   "max_position_embeddings": 65536,
-  "model_type": "hackathon_write",
   "num_attention_heads": 48,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 56,

   "initializer_range": 0.02,
   "intermediate_size": 16384,
   "max_position_embeddings": 65536,
+  "model_type": "llma2",
   "num_attention_heads": 48,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 56,