初始化项目，由ModelHub XC社区提供模型

Model: Neura-Tech-AI/Neuron-14B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+Neuron-14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

Neuron-14B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d17dc7a94b1fb434d0e609b83b9e79efb16202cd1acbbf7539c9110b56fe3e6
+size 12124683616

README.md

@@ -0,0 +1,65 @@
+---
+language:
+- en
+- hi
+tags:
+- neuron
+- neura-tech
+- 14B
+- text-generation
+- qwen2
+- neural-networks
+license: apache-2.0
+datasets:
+- custom-neura-tech-data
+metrics:
+- accuracy
+---
+
+# 🧠 Neuron-14B: The Official Intelligence of Neura Tech
+
+**Neuron-14B** is a high-performance Large Language Model (LLM) developed by **Neura Tech**. It serves as the flagship model for advanced reasoning, creative synthesis, and multilingual communication.
+
+---
+
+## 🏢 Organization Identity
+* **Company**: Neura Tech
+* **Project Name**: Neuron
+* **Lead Architect**: Anandnrnnffn
+
+## 📊 Model Specifications
+* **Architecture**: Optimized Transformer (Fine-tuned from Qwen2)
+* **Parameters**: ~15 Billion
+* **Precision**: BF16 (Bfloat16)
+* **Context Window**: 131,072 tokens
+* **License**: Apache-2.0 (Open Source)
+
+## 🎯 Core Capabilities
+* **Advanced Reasoning**: Capable of solving complex logical and mathematical queries.
+* **Multilingual Proficiency**: Highly optimized for English and Hindi (including Hinglish).
+* **Instruction Following**: Specifically tuned to follow complex user prompts with high precision.
+* **Creative Synthesis**: Exceptional at generating scripts, stories, and technical documentation.
+  
+## 📜 License & Usage
+This model is licensed under the Apache-2.0 License. This means you are free to use, modify, and distribute this model, provided that you credit Neura Tech as the original creator.
+
+## 🛠️ Quick Start (Python)
+To use **Neuron-14B**, load it via the Hugging Face `transformers` library:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Anandnrnnffn/Neura-Tech-14B-Weights"
+
+# Load Neuron-14B Tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# Load Model Weights
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype="auto"
+)
+```
+
+## © 2026 Neura Tech. All Rights Reserved.

config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+base_model: Anandnrnnffn/Neuron-14B
+checkpoints:
+- Anandnrnnffn/Neuron-14B-Identity-Adapter
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - adapters:
+    - Anandnrnnffn/Neuron-14B-Identity-Adapter
+    layer_range:
+    - 0
+    - 48
+    model: Anandnrnnffn/Neuron-14B

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d196b6f63537fd11dce9567bd2a5b1ae67ad77929c500c2b0e18d7c885195b
+size 4907454920

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968fb2f47bfaa0876c39cb801fdb226ae539c0e4c78ad3d7d0ae91630235ada3
+size 4954847280

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96dc8aad910fe24bdc64cbbefe112cbaa7293109145b7a1e85ff6c8a92d0b0a1
+size 4954847272

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68099ecdb01ac62b046803dca1812394aa1ddf3d3dfda044e3890fbdd3b6c8a
+size 4954847272

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bea2e0343223f0b4a13cade7ae5588d13f5ba759ebbf7700766a5f2cd7b913f
+size 4954847272

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5345c3475fd7d2eb5e5cc7ea96fcc74cb3708f8d1c3f29443598cb49e4ddc3
+size 4813289328

model.safetensors.index.json

@@ -0,0 +1,587 @@
+{
+  "metadata": {
+    "total_size": 29540067328,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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    {%- else %}\n        {{- 'You are Neuron-14B, a powerful AI assistant created by Anandnrnnffn and the Neura Tech Team. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are Neuron-14B, created by Anandnrnnffn and the Neura Tech Team. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) 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{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}