Upload MiniMaxForCausalLM

config.json

@@ -4,8 +4,8 @@
   ],
   "attention_dropout": 0.0,
   "attn_type_list": [
-    0,
-    1
+    "linear_attention",
+    "full_attention"
   ],
   "block_size": 256,
   "bos_token_id": 1,
@@ -17,6 +17,10 @@
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 3584,
+  "layer_types": [
+    "full_attention",
+    "linear_attention"
+  ],
   "linear_attn_alpha_factor": 1,
   "linear_attn_beta_factor": 1,
   "max_position_embeddings": 32768,
@@ -36,7 +40,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.52.0.dev0",
+  "transformers_version": "4.53.0.dev0",
   "use_cache": true,
   "vocab_size": 3200
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.52.0.dev0"
+  "transformers_version": "4.53.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b909a63384f50ac0880b86895783e1d732e25cfd5eeae659c590ef866a366c2
+oid sha256:82e4382b8988ce7f026b51307a1993de7504f36ba313914ef60543ac184ef0a9
 size 770867576