2d5f1cf2bd87ebcf23f9635326508c7b4b33df3d42cc64dde1f4e82d02efab3c

README.md

@@ -0,0 +1,41 @@
+---
+base_model: tiiuae/falcon-mamba-7b-instruct
+datasets:
+- tiiuae/falcon-refinedweb
+- HuggingFaceFW/fineweb-edu
+language:
+- en
+license: other
+license_name: falcon-mamba-7b-license
+license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
+pipeline_tag: text-generation
+tags:
+- mlx
+inference: true
+---
+
+# mlx-community/falcon-mamba-7b-8bit-instruct
+
+The Model [mlx-community/falcon-mamba-7b-8bit-instruct](https://huggingface.co/mlx-community/falcon-mamba-7b-8bit-instruct) was converted to MLX format from [tiiuae/falcon-mamba-7b-instruct](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct) using mlx-lm version **0.19.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/falcon-mamba-7b-8bit-instruct")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,42 @@
+{
+    "architectures": [
+        "FalconMambaForCausalLM"
+    ],
+    "bos_token_id": 8,
+    "conv_kernel": 4,
+    "eos_token_id": 11,
+    "expand": 16,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.1,
+    "intermediate_size": 8192,
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "falcon_mamba",
+    "num_hidden_layers": 64,
+    "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rescale_prenorm_residual": false,
+    "residual_in_fp32": true,
+    "state_size": 16,
+    "tie_word_embeddings": false,
+    "time_step_floor": 0.0001,
+    "time_step_init_scheme": "random",
+    "time_step_max": 0.1,
+    "time_step_min": 0.001,
+    "time_step_rank": 256,
+    "time_step_scale": 1.0,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.44.0.dev0",
+    "use_bias": false,
+    "use_cache": true,
+    "use_conv_bias": true,
+    "use_mambapy": false,
+    "vocab_size": 65024
+}

model.safetensors.index.json

@@ -0,0 +1,1166 @@
+{
+    "metadata": {
+        "total_size": 7738761216
+    },
+    "weight_map": {
+        "backbone.embeddings.biases": "model-00001-of-00002.safetensors",
+        "backbone.embeddings.scales": "model-00001-of-00002.safetensors",
+        "backbone.embeddings.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.0.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.1.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.10.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.11.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.12.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.13.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.14.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.15.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.16.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.17.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.18.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.19.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.2.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.20.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.21.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.22.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.23.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.24.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.25.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.26.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.27.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.28.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.29.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.3.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.30.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.31.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.32.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.33.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.34.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.35.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.36.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.37.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.38.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.39.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.4.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.40.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.41.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.42.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.43.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.44.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.45.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.45.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.46.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.47.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.48.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.49.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.5.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.5.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.50.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.50.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.51.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.52.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.53.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.54.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.55.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.56.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.57.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.58.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.59.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.6.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.6.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.60.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.60.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.61.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.62.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.A_log": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.D": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.dt_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.dt_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.in_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.in_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.out_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.out_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.x_proj.biases": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.x_proj.scales": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.63.norm.weight": "model-00002-of-00002.safetensors",
+        "backbone.layers.7.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.7.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.8.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.A_log": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.D": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.dt_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.dt_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.in_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.in_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.out_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.out_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.x_proj.biases": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.x_proj.scales": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
+        "backbone.layers.9.norm.weight": "model-00001-of-00002.safetensors",
+        "backbone.norm_f.weight": "model-00002-of-00002.safetensors",
+        "lm_head.biases": "model-00002-of-00002.safetensors",
+        "lm_head.scales": "model-00002-of-00002.safetensors",
+        "lm_head.weight": "model-00002-of-00002.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    "assistant",
+    "<|begin_of_text|>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": ">>TITLE<<",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,129 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "assistant",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    "assistant",
+    "<|begin_of_text|>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": ">>TITLE<<",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}