Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,32 @@
+{
+  "model_type": "nandi",
+  "vocab_size": 131072,
+  "hidden_size": 832,
+  "intermediate_size": 2496,
+  "num_hidden_layers": 16,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 4,
+  "hidden_act": "silu",
+  "max_position_embeddings": 2048,
+  "initializer_range": 0.008,
+  "rms_norm_eps": 1e-05,
+  "use_cache": true,
+  "pad_token_id": null,
+  "bos_token_id": 1,
+  "eos_token_id": 0,
+  "pretraining_tp": 1,
+  "tie_word_embeddings": true,
+  "rope_parameters": {
+    "rope_theta": 100000
+  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "mlp_bias": false,
+  "factorized_embedding": true,
+  "embedding_rank": 196,
+  "layer_sharing": true,
+  "layer_sharing_repeats": 2,
+  "z_loss_enabled": true,
+  "z_loss_coefficient": 0.0001,
+  "torch_dtype": "bfloat16"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1360813fad3084b773580e8f138969c2ba9052a7284fc71e72b77be20ae14fc
+size 306842392

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc858b896e5a8c86097420a23a90b8a0ad4d2ad23250e1fae99b89f525120c90
+size 12460256

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "bos_token_id": 1,
+  "eos_token": "<|endoftext|>",
+  "eos_token_id": 0,
+  "pad_token": "<|pad|>",
+  "pad_token_id": 3,
+  "model_max_length": 2048,
+  "tokenizer_class": "NandiTokenizer",
+  "unk_token": "<|endoftext|>"
+}