Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen3-1.7B-CSQA-NdLinearLoRA.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9dbc1819dbd6f801bc1c052f07073c0c3affd9094460af3ed7881cd9502a076
+size 8131640472

README.md

@@ -1,3 +1,67 @@
----
-license: apache-2.0
----
+---
+license: mit
+language: en
+---
+
+# NdLinear-LoRA Fine-Tuned Models
+
+This repository contains a collection of language models fine-tuned using a custom NdLinear-LoRA architecture. NdLinear-LoRA is a variant of Low-Rank Adaptation (LoRA) that reshapes weight matrices into N-dimensional tensors and applies a factorized linear transformation for parameter-efficient fine-tuning.
+
+## Available Models
+
+Below is a list of the fine-tuned models. For best results, it's recommended to host each model in its own repository on the Hugging Face Hub.
+
+| Fine-Tuned Model Name                            | Base Model                 | Fine-Tuning Dataset |
+| ------------------------------------------------ | -------------------------- | ------------------- |
+| `Meta-Llama-3-8B-CSQA-NdLinearLoRA`              | `meta-llama/Llama-3-8B`    | `commonsense_qa`    |
+| `Meta-Llama-3-8B-Math10K-NdLinearLoRA`           | `meta-llama/Llama-3-8B`    | `lmms-lab/Math10K`  |
+| `Qwen3-1.7B-CSQA-NdLinearLoRA`                   | `Qwen/Qwen3-1.7B-Base`     | `commonsense_qa`    |
+| `Qwen3-1.7B-Math10K-NdLinearLoRA`                | `Qwen/Qwen3-1.7B-Base`     | `lmms-lab/Math10K`  |
+
+## How to Use
+
+Because these models use a custom architecture, you must pass `trust_remote_code=True` when loading them. This allows the `transformers` library to download and use the `modeling_ndlinear.py` file that should be included in each model's repository.
+
+**Dependencies:** Before you start, make sure you have the necessary libraries installed:
+```bash
+pip install torch transformers safetensors huggingface_hub accelerate
+pip install ndlinear
+```
+
+### Example Loading Script
+This script will work for any of the models listed above. Just change the `REPO_ID`.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# --- Example Usage ---
+
+# 1. Choose the model you want to use from the table above
+#    Replace "YourUsername" with your Hugging Face username or organization.
+REPO_ID = "YourUsername/Qwen3-1.7B-Math10K-NdLinearLoRA" 
+
+# 2. Load the model and tokenizer
+# `trust_remote_code=True` is required to load the custom architecture.
+print(f"Loading model: {REPO_ID}")
+model = AutoModelForCausalLM.from_pretrained(
+    REPO_ID,
+    torch_dtype="auto",
+    device_map="auto",
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(REPO_ID)
+print("Model and tokenizer loaded successfully.")
+
+
+# 3. Generate text
+# This prompt is geared for a math model. Adjust it for a QA model if needed.
+prompt = "### Instruction:\\nSolve the following math problem: If a train travels at 60 miles per hour, how long does it take to travel 180 miles?\\n\\n### Solution:\\n"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(**inputs, max_new_tokens=150, eos_token_id=tokenizer.eos_token_id)
+
+print("\\n--- Generated Output ---")
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+``` 

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

modeling_ndlinear.py

@@ -0,0 +1,53 @@
+import torch
+import torch.nn as nn
+from ndlinear import NdLinear
+
+# This file contains the custom building blocks for the NdLinear-LoRA architecture.
+# It should be in the same directory as the model when loading it.
+
+def find_factor(n):
+    """Finds the most balanced integer factors for n."""
+    for i in range(int(n ** 0.5), 0, -1):
+        if n % i == 0:
+            return (i, n // i)
+    return (1, n)
+
+class NdLinearLoRA(nn.Module):
+    """The NdLinear-LoRA adapter layer."""
+    def __init__(self, d_in, d_out, alpha=1.0, dropout=0.0):
+        super().__init__()
+        self.d_in = d_in
+        self.d_out = d_out
+        self.in_factors = find_factor(d_in)
+        self.out_factors = find_factor(d_out)
+        self.adapter = NdLinear(
+            input_dims=self.in_factors,
+            hidden_size=self.out_factors,
+            transform_outer=False,
+            bias=False
+        )
+        self.scaling = alpha
+        self.drop = nn.Dropout(dropout)
+
+    def forward(self, x):
+        orig_shape = x.shape
+        x = self.drop(x).view(-1, *self.in_factors)
+        y = self.adapter(x).view(*orig_shape[:-1], self.d_out)
+        return y * self.scaling
+
+class LinearWithNdLinearLoRA(nn.Module):
+    """A nn.Linear layer wrapped with the NdLinear-LoRA adapter."""
+    def __init__(self, base_layer, alpha=1.0, dropout=0.0):
+        super().__init__()
+        self.base_layer = base_layer
+        for param in self.base_layer.parameters():
+            param.requires_grad = False
+        self.adapter = NdLinearLoRA(
+            d_in=self.base_layer.in_features,
+            d_out=self.base_layer.out_features,
+            alpha=alpha,
+            dropout=dropout
+        )
+
+    def forward(self, x):
+        return self.base_layer(x) + self.adapter(x) 

ndlinear.py

@@ -0,0 +1,82 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+
+
+class NdLinear(nn.Module):
+    def __init__(self, input_dims: tuple, hidden_size: tuple, transform_outer=True, bias: bool = True):
+        """
+        NdLinear: A PyTorch layer for projecting tensors into multi-space representations.
+        
+        Unlike conventional embedding layers that map into a single vector space, NdLinear 
+        transforms tensors across a collection of vector spaces, capturing multivariate structure 
+        and topical information that standard deep learning architectures typically lose.
+
+        Args:
+            input_dims (tuple): Shape of input tensor (excluding batch dimension).
+            hidden_size (tuple): Target hidden dimensions after transformation.
+        """
+        super(NdLinear, self).__init__()
+
+        if len(input_dims) != len(hidden_size):
+            raise Exception("Input shape and hidden shape do not match.")
+
+        self.input_dims = input_dims
+        self.hidden_size = hidden_size
+        self.num_layers = len(input_dims)  # Must match since dims are equal
+        # self.relu = nn.ReLU() # self.relu is not being used.
+        self.transform_outer = transform_outer
+        self.bias = bias
+
+        # Define transformation layers per dimension
+        self.align_layers = nn.ModuleList([
+            nn.Linear(input_dims[i], hidden_size[i], bias=self.bias) for i in range(self.num_layers)
+        ])
+
+
+    def forward(self, X):
+        """
+        Forward pass to project input tensor into a new multi-space representation.
+        - Incrementally transposes, flattens, applies linear layers, and restores shape.
+
+        Expected Input Shape: [batch_size, *input_dims]
+        Output Shape: [batch_size, *hidden_size]
+
+        Args:
+            X (torch.Tensor): Input tensor with shape [batch_size, *input_dims]
+
+        Returns:
+            torch.Tensor: Output tensor with shape [batch_size, *hidden_size]
+        """
+        num_transforms = self.num_layers  # Number of transformations
+        
+        # Define iteration order
+        # transform_indices = range(num_transforms) if transform_outer else reversed(range(num_transforms))
+
+        for i in range(num_transforms):
+            if self.transform_outer:
+                layer = self.align_layers[i]
+                transpose_dim = i + 1
+            else:
+                layer = self.align_layers[num_transforms - (i+1)]
+                transpose_dim = num_transforms - i
+
+            # Transpose the selected dimension to the last position
+            X = torch.transpose(X, transpose_dim, num_transforms).contiguous()
+
+            # Store original shape before transformation
+            X_size = X.shape[:-1]
+
+            # Flatten everything except the last dimension
+            X = X.view(-1, X.shape[-1])
+
+            # Apply transformation
+            X = layer(X)
+            
+            # Reshape back to the original spatial structure (with new embedding dim)
+            X = X.view(*X_size, X.shape[-1])
+
+            # Transpose the dimension back to its original position
+            X = torch.transpose(X, transpose_dim, num_transforms).contiguous()
+
+        return X

ndlinear_lora_config.json

@@ -0,0 +1,2372 @@
+{
+  "model_name": "Qwen/Qwen3-1.7B-Base",
+  "lora_r": 1,
+  "lora_alpha": 1,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "use_factorized": true,
+  "wrapped_modules": {
+    "model.layers.0.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.0.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.0.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.0.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.0.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.0.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.0.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.1.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.1.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.1.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.1.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.1.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.1.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.1.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.2.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.2.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.2.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.2.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.2.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.2.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.2.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.3.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.3.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.3.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.3.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.3.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.3.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.3.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.4.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.4.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.4.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.4.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.4.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.4.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.4.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.5.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.5.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.5.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.5.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.5.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.5.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.5.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.6.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.6.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.6.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.6.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.6.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.6.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.6.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.7.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.7.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.7.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.7.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.7.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.7.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.7.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.8.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.8.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.8.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.8.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.8.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.8.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.8.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.9.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.9.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.9.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.9.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.9.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.9.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.9.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.10.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.10.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.10.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.10.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.10.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.10.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.10.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.11.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.11.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.11.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.11.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.11.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.11.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.11.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.12.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.12.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.12.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.12.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.12.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.12.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.12.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.13.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.13.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.13.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.13.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.13.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.13.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.13.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.14.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.14.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.14.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.14.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.14.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.14.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.14.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.15.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.15.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.15.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.15.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.15.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.15.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.15.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.16.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.16.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.16.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.16.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.16.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.16.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.16.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.17.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.17.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.17.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.17.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.17.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.17.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.17.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.18.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.18.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.18.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.18.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.18.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.18.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.18.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.19.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.19.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.19.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.19.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.19.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.19.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.19.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.20.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.20.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.20.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.20.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.20.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.20.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.20.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.21.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.21.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.21.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.21.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.21.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.21.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.21.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.22.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.22.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.22.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.22.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.22.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.22.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.22.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.23.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.23.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.23.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.23.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.23.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.23.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.23.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.24.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.24.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.24.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.24.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.24.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.24.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.24.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.25.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.25.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.25.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.25.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.25.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.25.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.25.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.26.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.26.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.26.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.26.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.26.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.26.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.26.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.27.self_attn.q_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.27.self_attn.k_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.27.self_attn.v_proj": {
+      "in_features": 2048,
+      "out_features": 1024,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        32
+      ]
+    },
+    "model.layers.27.self_attn.o_proj": {
+      "in_features": 2048,
+      "out_features": 2048,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    },
+    "model.layers.27.mlp.gate_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.27.mlp.up_proj": {
+      "in_features": 2048,
+      "out_features": 6144,
+      "in_factors": [
+        32,
+        64
+      ],
+      "out_factors": [
+        64,
+        96
+      ]
+    },
+    "model.layers.27.mlp.down_proj": {
+      "in_features": 6144,
+      "out_features": 2048,
+      "in_factors": [
+        64,
+        96
+      ],
+      "out_factors": [
+        32,
+        64
+      ]
+    }
+  },
+  "best_epoch": 2,
+  "early_stopped": false,
+  "best_val_loss": 0.12033694753423334
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe925c3e0de1216e7362dbeff59cc876498c754045f4d3bd4cca567b28c11a6
+size 6887279983

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a224a732c0c9a3eadea504a5629233b88761c3105d1f1b4a60161847a0709c32
+size 11422753

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}