change config

config.json

@@ -12,10 +12,10 @@
   "intermediate_size": 256,
   "max_position_embeddings": 32768,
   "model_type": "mixtral",
-  "num_attention_heads": 32,
+  "num_attention_heads": 2,
   "num_experts_per_tok": 4,
   "num_hidden_layers": 12,
-  "num_key_value_heads": 8,
+  "num_key_value_heads": 1,
   "num_local_experts": 4,
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,
@@ -23,8 +23,8 @@
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 32005
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a260b8590ae82e8e99c7b9963bebb6c5279db84f8a1440845b2ed6546e72aef6
-size 13194088
+oid sha256:3e68fe9d7fd1316bb75d8ddd3450a9deaec8d3ef684e84c55517fd26b9848a83
+size 26459296