artek0chumak
/

TestMixtral

Text Generation

text-generation-inference

Model card Files Files and versions

artek0chumak commited on Apr 10, 2024

Commit

ef8246f

·

verified ·

1 Parent(s): d0030da

change config

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -12,10 +12,10 @@
   "intermediate_size": 256,
   "max_position_embeddings": 32768,
   "model_type": "mixtral",
-  "num_attention_heads": 2,
   "num_experts_per_tok": 4,
   "num_hidden_layers": 12,
-  "num_key_value_heads": 1,
   "num_local_experts": 4,
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,
@@ -23,7 +23,7 @@
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 32005

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

model.safetensors CHANGED Viewed

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

 version https://git-lfs.github.com/spec/v1
+oid sha256:bc8649a3911f75a1281729ab4ff64717adc063e9dbdf70d611c56ddb3d2da868
+size 13243240