mixed mxfp8/nvfp4/bf16 MLX conversion of Qwen/Qwen3.8-27B (mlx-vlm 0.6.17)

README.md

@@ -32,7 +32,7 @@ This repository contains [`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.
 | MTP head | bfloat16 |
 | Vision tower | bfloat16 |
 
-- Effective size: ~24 GB (7.8 bits per weight), base model is ~54 GB in bfloat16.
+- Effective size: ~24 GB (7.9 bits per weight), base model is ~54 GB in bfloat16.
 - Quantized modules: mxfp8 (group_size=32, bits=8) / nvfp4 (group_size=16, bits=4); bfloat16 modules are stored as-is. Per-module precision is detected from the presence of `.scales` tensors.
 
 ## MTP

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1eb950e11d79a54ab33a2d829a06e289e9802b06806090b917fd314645196e
-size 5335899843
+oid sha256:3ee3e79fa11d98687022b62cc0892a92a477325e219ea1e027c74d167815d4a5
+size 5342651393

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10f436b88df3d3c5f4e5fa3b6d571a789345ecb464335038ec8829098dd9280
-size 5342300312
+oid sha256:08720813d66efcec558bff958cc5a35427aec64dd719571ce7df952dd02e0db4
+size 5342300272

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b686a577e5fc8af9aba79de3fca59a933419d17d05b6cf3ff8b9e002f687f8
-size 5342300264
+oid sha256:95f201102f6c75c068c43d5f9fc733541da308105875c5c5c0d4cf38e73d40e5
+size 5342300284

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b660fa3658edbcaf7d868e45634d7e65386709797b784c82e256103dad3dc8e
-size 4154290877
+oid sha256:3562fdbe5643e6af37d696b2b0b9c20fde830853c14e68075ad2daba3e24b445
+size 4532413904

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 23566767328
+        "total_size": 23951648224
     },
     "weight_map": {
         "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
@@ -429,46 +429,46 @@
         "language_model.model.layers.26.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.A_log": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_b.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.A_log": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_b.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.29.linear_attn.A_log": "model-00003-of-00005.safetensors",
         "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
@@ -889,46 +889,46 @@
         "language_model.model.layers.46.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.46.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.46.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.47.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.A_log": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_a.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_b.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_qkv.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_z.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.out_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.48.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.47.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.47.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.A_log": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_a.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_b.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_qkv.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_z.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.out_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.48.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.48.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.48.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.48.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.48.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.48.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.48.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.48.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.48.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.49.input_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.49.linear_attn.A_log": "model-00004-of-00005.safetensors",
         "language_model.model.layers.49.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
@@ -1287,46 +1287,46 @@
         "language_model.model.layers.63.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.63.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.63.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.A_log": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_a.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_b.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.A_log": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_a.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_b.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.linear_attn.A_log": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
@@ -1370,10 +1370,8 @@
         "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.0.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.0.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.0.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1384,10 +1382,8 @@
         "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.1.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.1.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.1.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1398,10 +1394,8 @@
         "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.10.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.10.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.10.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1412,10 +1406,8 @@
         "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.11.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.11.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.11.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1426,10 +1418,8 @@
         "vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.12.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.12.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.12.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1440,10 +1430,8 @@
         "vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.13.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.13.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.13.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1454,10 +1442,8 @@
         "vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.14.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.14.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.14.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1468,10 +1454,8 @@
         "vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.15.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.15.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.15.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1482,10 +1466,8 @@
         "vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.16.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.16.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.16.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1496,10 +1478,8 @@
         "vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.17.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.17.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.17.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1510,10 +1490,8 @@
         "vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.18.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.18.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.18.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1524,10 +1502,8 @@
         "vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.19.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.19.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.19.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1538,10 +1514,8 @@
         "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.2.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.2.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.2.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1552,10 +1526,8 @@
         "vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.20.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.20.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.20.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1566,10 +1538,8 @@
         "vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.21.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.21.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.21.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1580,10 +1550,8 @@
         "vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.22.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.22.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.22.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1594,10 +1562,8 @@
         "vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.23.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.23.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.23.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1608,10 +1574,8 @@
         "vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.24.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.24.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.24.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.24.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1622,10 +1586,8 @@
         "vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.25.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.25.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.25.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.25.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1636,10 +1598,8 @@
         "vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.26.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.26.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.26.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.26.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1650,10 +1610,8 @@
         "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.3.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.3.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.3.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1664,10 +1622,8 @@
         "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.4.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.4.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.4.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1678,10 +1634,8 @@
         "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.5.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.5.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.5.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1692,10 +1646,8 @@
         "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.6.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.6.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.6.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1706,10 +1658,8 @@
         "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.7.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.7.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.7.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1720,10 +1670,8 @@
         "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.8.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.8.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.8.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
@@ -1734,10 +1682,8 @@
         "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.9.mlp.linear_fc1.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
-        "vision_tower.blocks.9.mlp.linear_fc2.scales": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.9.norm1.bias": "model-00001-of-00005.safetensors",
         "vision_tower.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",