Update tiny models for Zamba2Model

config.json

@@ -0,0 +1,67 @@
+{
+  "adapter_rank": 128,
+  "add_bias_linear": false,
+  "architectures": [
+    "Zamba2Model"
+  ],
+  "attention_dropout": 0.0,
+  "attention_head_dim": 16,
+  "attention_hidden_size": 32,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "chunk_size": 8,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_mamba_act": "silu",
+  "hidden_size": 16,
+  "hybrid_layer_ids": [
+    1,
+    2
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 4,
+  "is_decoder": true,
+  "kv_channels": 8,
+  "layers_block_type": [
+    "linear_attention",
+    "hybrid",
+    "hybrid"
+  ],
+  "mamba_d_conv": 4,
+  "mamba_d_state": 2,
+  "mamba_dt_rank": "auto",
+  "mamba_expand": 2,
+  "mamba_headdim": 4,
+  "mamba_ngroups": 8,
+  "max_position_embeddings": 512,
+  "model_type": "zamba2",
+  "n_mamba_heads": 8,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 3,
+  "num_key_value_heads": 2,
+  "num_logits_to_keep": 1,
+  "num_mem_blocks": 1,
+  "num_query_groups": 2,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "time_step_floor": 0.0001,
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "transformers_version": "5.16.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_long_context": false,
+  "use_mamba_kernels": false,
+  "use_mem_eff_path": false,
+  "use_mem_rope": true,
+  "use_shared_attention_adapter": false,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022875c128630b8723edd32c89c211db0b8fddc1d28b40fa119c8032238465d7
+size 2125448

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}