Update tiny models for Mamba2ForCausalLM

config.json

@@ -0,0 +1,45 @@
+{
+  "activation_function": "silu",
+  "architectures": [
+    "Mamba2ForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "chunk_size": 8,
+  "conv_kernel": 4,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "expand": 2,
+  "gradient_checkpointing": false,
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.1,
+  "is_decoder": true,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mamba2",
+  "n_groups": 8,
+  "n_positions": 512,
+  "num_heads": 8,
+  "num_hidden_layers": 2,
+  "pad_token_id": 1,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "state_size": 2,
+  "tie_word_embeddings": false,
+  "time_step_floor": 0.0001,
+  "time_step_limit": [
+    0.0,
+    {
+      "__float__": "Infinity"
+    }
+  ],
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 2,
+  "transformers_version": "5.16.0.dev0",
+  "type_vocab_size": 16,
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "vocab_size": 50277
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55e3d1c3b0a4133b0f966b62880742ce1303a61a58f8fcf7d2b9712f578fc7c
+size 12937320

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}