Upload 10 files

args.json

@@ -0,0 +1,25 @@
+{
+    "data_dir": "/code/VLA/datasets/SSR-CoT",
+    "clip_path": "/code/VLA/models/clip-vit-large-patch14-336",
+    "siglip_path": "/code/VLA/models/siglip-so400m-patch14-384",
+    "segformer_path": "/code/VLA/models/segmentation_models/segformer-b5-finetuned-ade-640-640",
+    "use_semantic": true,
+    "n_tor": 10,
+    "max_length": [
+        256,
+        1024,
+        256
+    ],
+    "lr": 2e-05,
+    "mamba": "/code/VLA/models/state-spaces/mamba-130m-hf",
+    "llm": "/code/VLA/models/Qwen2.5-7B",
+    "epochs": 2,
+    "batch_size_per_gpu": 2,
+    "gradient_accumulation_steps": 4,
+    "warmup_ratio": 0.02,
+    "output_dir": "checkpoints/SSR-MIDI-trimodal/2025-09-28 17:03:11",
+    "use_precomputed": true,
+    "precomputed_dir": "/code/VLA/datasets/SSR-CoT/precomputed_features",
+    "num_workers": 4,
+    "use_gradient_checkpointing": true
+}

losses.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e28af33c911c183971954dd251c3a9bf043a34bbfd701520a7a92f3685da38
+size 1198832

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d84e707c4efc45217085fb651ca48fc31b971546d8f3dbf89e8fd513fcae28e
+size 4848299192

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe607b3ce54203f89e568532ed6cd44f5e263088097b462b365136fd004a859c
+size 4932744176

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3636052cb5546b6bb0aaad9c50394bc72e53e4a6e3bc295faa7211ab6d05a678
+size 4932744192

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fed3ede0680677470ce8087b0550917ca7a1079fb6c58f9a09dc13d0c584b4c
+size 4998852568

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74bcdbf96284a4a3869103936d7fae0d9eff89dc03299890be1065a342486fc
+size 4984124584

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff3d7848567ac546d11414941bff5f5e33325ad8624c4521831744a392ecb28
+size 4272136296

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0cc1f634492e37c918d6e721fb90140a96d7e38912b1af7087c32baec07817
+size 2242408944

model.safetensors.index.json

@@ -0,0 +1,605 @@
+{
+  "metadata": {
+    "total_size": 31211240448
+  },
+  "weight_map": {
+    "depth_proj.0.bias": "model-00001-of-00007.safetensors",
+    "depth_proj.0.weight": "model-00001-of-00007.safetensors",
+    "depth_proj.2.bias": "model-00001-of-00007.safetensors",
+    "depth_proj.2.weight": "model-00001-of-00007.safetensors",
+    "image_proj.0.bias": "model-00001-of-00007.safetensors",
+    "image_proj.0.weight": "model-00001-of-00007.safetensors",
+    "image_proj.2.bias": "model-00001-of-00007.safetensors",
+    "image_proj.2.weight": "model-00001-of-00007.safetensors",
+    "llm.lm_head.weight": "model-00007-of-00007.safetensors",
+    "llm.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.norm.weight": "model-00006-of-00007.safetensors",
+    "mamba.backbone.embeddings.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.0.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.1.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.10.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.11.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.12.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.13.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.14.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.15.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.16.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.17.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.18.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.19.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.2.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.20.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.21.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.22.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.23.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.3.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.4.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.5.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.6.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.7.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.8.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.A_log": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.D": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.dt_proj.bias": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.dt_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.mixer.x_proj.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.layers.9.norm.weight": "model-00001-of-00007.safetensors",
+    "mamba.backbone.norm_f.weight": "model-00001-of-00007.safetensors",
+    "mamba.lm_head.weight": "model-00001-of-00007.safetensors",
+    "semantic_proj.0.bias": "model-00001-of-00007.safetensors",
+    "semantic_proj.0.weight": "model-00001-of-00007.safetensors",
+    "semantic_proj.2.bias": "model-00001-of-00007.safetensors",
+    "semantic_proj.2.weight": "model-00001-of-00007.safetensors",
+    "tor_proj.0.bias": "model-00007-of-00007.safetensors",
+    "tor_proj.0.weight": "model-00007-of-00007.safetensors",
+    "tor_proj.2.bias": "model-00007-of-00007.safetensors",
+    "tor_proj.2.weight": "model-00007-of-00007.safetensors"
+  }
+}