Update tiny models for MellumModel

config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "MellumModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "head_dim": 16,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 512,
+  "mlp_layer_types": [
+    "dense",
+    "sparse"
+  ],
+  "model_type": "mellum",
+  "moe_intermediate_size": 16,
+  "norm_topk_prob": true,
+  "num_attention_heads": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 500000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": 1024,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 98304
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54e0bd69730471fb1736c3cc71e6d179ccede0f3c5fdcccb0b19e07cf931f30
+size 12683856

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}