SE6446
/

Tiny-llamix_2x1B

Text Generation

Mixture of Experts

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

SE6446 commited on Jan 12

Commit

f6f76c8

•

1 Parent(s): 0a79c3e

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
-  "model_type": "llama",
   "num_attention_heads": 32,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 22,

 {
   "architectures": [
+    "MixtralForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
+  "model_type": "mixtral",
   "num_attention_heads": 32,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 22,