Upload Transformer

README.md

@@ -1,3 +1,6 @@
+---
+{}
+---
 <div align="center">
 
 ![logo](./images/logo.png)

config.json

@@ -1,33 +1,32 @@
-{
-  "_name_or_path": "minimind-small-T",
-  "architectures": [
-    "Transformer"
-  ],
-  "auto_map": {
-    "AutoConfig": "LMConfig.LMConfig",
-    "AutoModelForCausalLM": "model.Transformer"
-  },
-  "aux_loss_alpha": 0.01,
-  "dim": 512,
-  "dropout": 0.0,
-  "flash_attn": true,
-  "hidden_dim": null,
-  "max_seq_len": 512,
-  "model_type": "minimind",
-  "multiple_of": 64,
-  "n_heads": 16,
-  "n_kv_heads": 8,
-  "n_layers": 8,
-  "n_routed_experts": 4,
-  "n_shared_experts": true,
-  "norm_eps": 1e-05,
-  "norm_topk_prob": true,
-  "num_experts_per_tok": 2,
-  "safe_serialization": false,
-  "scoring_func": "softmax",
-  "seq_aux": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "use_moe": false,
-  "vocab_size": 6400
-}
+{
+  "_name_or_path": "minimind-v1-small",
+  "architectures": [
+    "Transformer"
+  ],
+  "auto_map": {
+    "AutoConfig": "LMConfig.LMConfig",
+    "AutoModelForCausalLM": "model.Transformer"
+  },
+  "aux_loss_alpha": 0.01,
+  "dim": 512,
+  "dropout": 0.0,
+  "flash_attn": true,
+  "hidden_dim": null,
+  "max_seq_len": 512,
+  "model_type": "minimind",
+  "multiple_of": 64,
+  "n_heads": 16,
+  "n_kv_heads": 8,
+  "n_layers": 8,
+  "n_routed_experts": 4,
+  "n_shared_experts": true,
+  "norm_eps": 1e-05,
+  "norm_topk_prob": true,
+  "num_experts_per_tok": 2,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "use_moe": false,
+  "vocab_size": 6400
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.44.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77975d6245af6914e61f0f0803f4c3e438b55b50927e261c8191d60ee9f62d8
+size 107537292