初始化项目，由ModelHub XC社区提供模型

Model: meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,39 @@
+---
+license: apache-2.0
+base_model:
+- meditsolutions/MSH-v1-Bielik-v2.3-Instruct-MedIT-merge
+- speakleash/Bielik-11B-v2.3-Instruct
+pipeline_tag: text-generation
+tags:
+- medit-lite
+- model-pruning
+- text-generation
+language:
+- pl
+- en
+---
+
+<div align="center">
+  <img src="https://i.ibb.co/6HbR84p/imagine-image-e5133e7c-9457-4539-a5e8-e59095e80345.png" alt="MSH-Lite" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;">
+</div>
+
+# Marsh Harrier Lite (MSH-Lite)
+
+Marsh Harrier Lite (MSH-Lite) is a compact, efficient version of the [MedIT Solutions MSH-v1-Bielik-v2.3-Instruct-MedIT-merge](meditsolutions/MSH-v1-Bielik-v2.3-Instruct-MedIT-merge) model, reduced to 7 billion parameters using advanced pruning techniques. This pruning retains the core functionality and efficiency of the original model while optimizing for reduced computational resource usage.
+
+## Key Features:
+- **Pruned Model**: Reduced from 11B to 7B parameters using the pruning method based on the [MedIT Solutions LLaMA pruning framework](https://github.com/MedITSolutionsKurman/llama-pruning).
+- **Optimized Performance**: Despite its reduced size, MSH-Lite delivers competitive performance across a wide array of NLP tasks.
+- **Bilingual Support**: Designed to handle both Polish (pl) and English (en) with high fluency.
+
+## Technical Details:
+- **Base Model**: [MSH-v1-Bielik-v2.3-Instruct-MedIT-merge](https://huggingface.co/meditsolutions/MSH-v1-Bielik-v2.3-Instruct-MedIT-merge)
+- **Parameter Count**: 7 billion
+- **Architecture**: Derived from Bielik's core architecture, with parameter optimization.
+- **Model Efficiency**: Ideal for deployments where computational efficiency is paramount.
+
+## Performance Highlights:
+To be done.
+
+### Acknowledgments:
+Gratitude to the **[SpeakLeash](https://speakleash.org)** project and **[ACK Cyfronet AGH](https://www.cyfronet.pl/)** for their contributions and collaboration.

added_tokens.json

@@ -0,0 +1,130 @@
+{
+  "<|control_100|>": 32099,
+  "<|control_101|>": 32100,
+  "<|control_102|>": 32101,
+  "<|control_103|>": 32102,
+  "<|control_104|>": 32103,
+  "<|control_105|>": 32104,
+  "<|control_106|>": 32105,
+  "<|control_107|>": 32106,
+  "<|control_108|>": 32107,
+  "<|control_109|>": 32108,
+  "<|control_10|>": 32009,
+  "<|control_110|>": 32109,
+  "<|control_111|>": 32110,
+  "<|control_112|>": 32111,
+  "<|control_113|>": 32112,
+  "<|control_114|>": 32113,
+  "<|control_115|>": 32114,
+  "<|control_116|>": 32115,
+  "<|control_117|>": 32116,
+  "<|control_118|>": 32117,
+  "<|control_119|>": 32118,
+  "<|control_11|>": 32010,
+  "<|control_120|>": 32119,
+  "<|control_121|>": 32120,
+  "<|control_122|>": 32121,
+  "<|control_123|>": 32122,
+  "<|control_124|>": 32123,
+  "<|control_125|>": 32124,
+  "<|control_126|>": 32125,
+  "<|control_127|>": 32126,
+  "<|control_128|>": 32127,
+  "<|control_12|>": 32011,
+  "<|control_13|>": 32012,
+  "<|control_14|>": 32013,
+  "<|control_15|>": 32014,
+  "<|control_16|>": 32015,
+  "<|control_17|>": 32016,
+  "<|control_18|>": 32017,
+  "<|control_19|>": 32018,
+  "<|control_20|>": 32019,
+  "<|control_21|>": 32020,
+  "<|control_22|>": 32021,
+  "<|control_23|>": 32022,
+  "<|control_24|>": 32023,
+  "<|control_25|>": 32024,
+  "<|control_26|>": 32025,
+  "<|control_27|>": 32026,
+  "<|control_28|>": 32027,
+  "<|control_29|>": 32028,
+  "<|control_30|>": 32029,
+  "<|control_31|>": 32030,
+  "<|control_32|>": 32031,
+  "<|control_33|>": 32032,
+  "<|control_34|>": 32033,
+  "<|control_35|>": 32034,
+  "<|control_36|>": 32035,
+  "<|control_37|>": 32036,
+  "<|control_38|>": 32037,
+  "<|control_39|>": 32038,
+  "<|control_40|>": 32039,
+  "<|control_41|>": 32040,
+  "<|control_42|>": 32041,
+  "<|control_43|>": 32042,
+  "<|control_44|>": 32043,
+  "<|control_45|>": 32044,
+  "<|control_46|>": 32045,
+  "<|control_47|>": 32046,
+  "<|control_48|>": 32047,
+  "<|control_49|>": 32048,
+  "<|control_50|>": 32049,
+  "<|control_51|>": 32050,
+  "<|control_52|>": 32051,
+  "<|control_53|>": 32052,
+  "<|control_54|>": 32053,
+  "<|control_55|>": 32054,
+  "<|control_56|>": 32055,
+  "<|control_57|>": 32056,
+  "<|control_58|>": 32057,
+  "<|control_59|>": 32058,
+  "<|control_60|>": 32059,
+  "<|control_61|>": 32060,
+  "<|control_62|>": 32061,
+  "<|control_63|>": 32062,
+  "<|control_64|>": 32063,
+  "<|control_65|>": 32064,
+  "<|control_66|>": 32065,
+  "<|control_67|>": 32066,
+  "<|control_68|>": 32067,
+  "<|control_69|>": 32068,
+  "<|control_6|>": 32005,
+  "<|control_70|>": 32069,
+  "<|control_71|>": 32070,
+  "<|control_72|>": 32071,
+  "<|control_73|>": 32072,
+  "<|control_74|>": 32073,
+  "<|control_75|>": 32074,
+  "<|control_76|>": 32075,
+  "<|control_77|>": 32076,
+  "<|control_78|>": 32077,
+  "<|control_79|>": 32078,
+  "<|control_7|>": 32006,
+  "<|control_80|>": 32079,
+  "<|control_81|>": 32080,
+  "<|control_82|>": 32081,
+  "<|control_83|>": 32082,
+  "<|control_84|>": 32083,
+  "<|control_85|>": 32084,
+  "<|control_86|>": 32085,
+  "<|control_87|>": 32086,
+  "<|control_88|>": 32087,
+  "<|control_89|>": 32088,
+  "<|control_8|>": 32007,
+  "<|control_90|>": 32089,
+  "<|control_91|>": 32090,
+  "<|control_92|>": 32091,
+  "<|control_93|>": 32092,
+  "<|control_94|>": 32093,
+  "<|control_95|>": 32094,
+  "<|control_96|>": 32095,
+  "<|control_97|>": 32096,
+  "<|control_98|>": 32097,
+  "<|control_99|>": 32098,
+  "<|control_9|>": 32008,
+  "<|function_call|>": 32004,
+  "<|function_list|>": 32002,
+  "<|function_output|>": 32003,
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/mkurman/gitlab/ai/model-trainer/checkpoints/bielik-v3-2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 8602,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 50,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32001,
+  "pad_token_id": 2,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b593454cbe7f48869ffda166d88c2b1ba0a197282a9458b00f9152d82cc9e2
+size 4988092808

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac3fd5a5f640eba54ec2786369170132b0fc6a844a8afe015e717580afcc04d
+size 4949722136

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e189a12aab2505aed80171342c4c786f2e2185cee2002cf322cf95f9508ba0fe
+size 4949738744

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76dea415cb2ed6384510275541485314ed466d2d3049a2447ca1935a61e89e99
+size 404152992

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 15291654144
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,160 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|function_list|>",
+    "<|function_output|>",
+    "<|function_call|>",
+    "<|control_6|>",
+    "<|control_7|>",
+    "<|control_8|>",
+    "<|control_9|>",
+    "<|control_10|>",
+    "<|control_11|>",
+    "<|control_12|>",
+    "<|control_13|>",
+    "<|control_14|>",
+    "<|control_15|>",
+    "<|control_16|>",
+    "<|control_17|>",
+    "<|control_18|>",
+    "<|control_19|>",
+    "<|control_20|>",
+    "<|control_21|>",
+    "<|control_22|>",
+    "<|control_23|>",
+    "<|control_24|>",
+    "<|control_25|>",
+    "<|control_26|>",
+    "<|control_27|>",
+    "<|control_28|>",
+    "<|control_29|>",
+    "<|control_30|>",
+    "<|control_31|>",
+    "<|control_32|>",
+    "<|control_33|>",
+    "<|control_34|>",
+    "<|control_35|>",
+    "<|control_36|>",
+    "<|control_37|>",
+    "<|control_38|>",
+    "<|control_39|>",
+    "<|control_40|>",
+    "<|control_41|>",
+    "<|control_42|>",
+    "<|control_43|>",
+    "<|control_44|>",
+    "<|control_45|>",
+    "<|control_46|>",
+    "<|control_47|>",
+    "<|control_48|>",
+    "<|control_49|>",
+    "<|control_50|>",
+    "<|control_51|>",
+    "<|control_52|>",
+    "<|control_53|>",
+    "<|control_54|>",
+    "<|control_55|>",
+    "<|control_56|>",
+    "<|control_57|>",
+    "<|control_58|>",
+    "<|control_59|>",
+    "<|control_60|>",
+    "<|control_61|>",
+    "<|control_62|>",
+    "<|control_63|>",
+    "<|control_64|>",
+    "<|control_65|>",
+    "<|control_66|>",
+    "<|control_67|>",
+    "<|control_68|>",
+    "<|control_69|>",
+    "<|control_70|>",
+    "<|control_71|>",
+    "<|control_72|>",
+    "<|control_73|>",
+    "<|control_74|>",
+    "<|control_75|>",
+    "<|control_76|>",
+    "<|control_77|>",
+    "<|control_78|>",
+    "<|control_79|>",
+    "<|control_80|>",
+    "<|control_81|>",
+    "<|control_82|>",
+    "<|control_83|>",
+    "<|control_84|>",
+    "<|control_85|>",
+    "<|control_86|>",
+    "<|control_87|>",
+    "<|control_88|>",
+    "<|control_89|>",
+    "<|control_90|>",
+    "<|control_91|>",
+    "<|control_92|>",
+    "<|control_93|>",
+    "<|control_94|>",
+    "<|control_95|>",
+    "<|control_96|>",
+    "<|control_97|>",
+    "<|control_98|>",
+    "<|control_99|>",
+    "<|control_100|>",
+    "<|control_101|>",
+    "<|control_102|>",
+    "<|control_103|>",
+    "<|control_104|>",
+    "<|control_105|>",
+    "<|control_106|>",
+    "<|control_107|>",
+    "<|control_108|>",
+    "<|control_109|>",
+    "<|control_110|>",
+    "<|control_111|>",
+    "<|control_112|>",
+    "<|control_113|>",
+    "<|control_114|>",
+    "<|control_115|>",
+    "<|control_116|>",
+    "<|control_117|>",
+    "<|control_118|>",
+    "<|control_119|>",
+    "<|control_120|>",
+    "<|control_121|>",
+    "<|control_122|>",
+    "<|control_123|>",
+    "<|control_124|>",
+    "<|control_125|>",
+    "<|control_126|>",
+    "<|control_127|>",
+    "<|control_128|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}