Half Epoch checkpoint:

11:27:54-941537 INFO Loading JSON datasets
Map: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 1365/1365 [00:05<00:00, 262.82 examples/s]
11:28:00-429977 INFO Getting model ready
11:28:00-437996 INFO Preparing for training
11:28:00-439851 INFO Creating LoRA model
11:28:00-893558 INFO Starting training
Training 'mixtral' model using (q, v) projections
Trainable params: 50,331,648 (1.1246 %), All params: 4,475,538,432 (Model: 4,425,206,784)
11:28:01-555106 INFO Log file 'train_dataset_sample.json' created in the 'logs' directory.
Step: 4 {'loss': 0.0668, 'grad_norm': 0.1359836459159851, 'learning_rate': 9.963736263736264e-06, 'epoch': 0.003663003663003663}
Step: 9 {'loss': 0.0916, 'grad_norm': 0.2279471606016159, 'learning_rate': 9.927472527472529e-06, 'epoch': 0.007326007326007326}
Step: 14 {'loss': 0.0753, 'grad_norm': 0.4511280357837677, 'learning_rate': 9.891208791208792e-06, 'epoch': 0.01098901098901099}
Step: 19 {'loss': 0.084, 'grad_norm': 0.24976688623428345, 'learning_rate': 9.854945054945056e-06, 'epoch': 0.014652014652014652}
Step: 24 {'loss': 0.0741, 'grad_norm': 0.09527433663606644, 'learning_rate': 9.81868131868132e-06, 'epoch': 0.018315018315018316}
Step: 29 {'loss': 0.076, 'grad_norm': 0.06122274696826935, 'learning_rate': 9.782417582417582e-06, 'epoch': 0.02197802197802198}
Step: 34 {'loss': 0.082, 'grad_norm': 0.26327070593833923, 'learning_rate': 9.746153846153847e-06, 'epoch': 0.02564102564102564}
Step: 39 {'loss': 0.0612, 'grad_norm': 0.2465166449546814, 'learning_rate': 9.70989010989011e-06, 'epoch': 0.029304029304029304}
Step: 44 {'loss': 0.0733, 'grad_norm': 0.08420123159885406, 'learning_rate': 9.673626373626375e-06, 'epoch': 0.03296703296703297}
Step: 49 {'loss': 0.0565, 'grad_norm': 0.25095030665397644, 'learning_rate': 9.637362637362638e-06, 'epoch': 0.03663003663003663}
Step: 54 {'loss': 0.0902, 'grad_norm': 0.33763477206230164, 'learning_rate': 9.601098901098903e-06, 'epoch': 0.040293040293040296}
Step: 59 {'loss': 0.1316, 'grad_norm': 0.5101003050804138, 'learning_rate': 9.564835164835166e-06, 'epoch': 0.04395604395604396}
Step: 64 {'loss': 0.1362, 'grad_norm': 0.45701834559440613, 'learning_rate': 9.528571428571429e-06, 'epoch': 0.047619047619047616}
Step: 69 {'loss': 0.1631, 'grad_norm': 0.563866376876831, 'learning_rate': 9.492307692307693e-06, 'epoch': 0.05128205128205128}
Step: 74 {'loss': 0.1354, 'grad_norm': 0.10952164232730865, 'learning_rate': 9.456043956043956e-06, 'epoch': 0.054945054945054944}
Step: 79 {'loss': 0.1858, 'grad_norm': 0.22133922576904297, 'learning_rate': 9.419780219780221e-06, 'epoch': 0.05860805860805861}
Step: 84 {'loss': 0.1611, 'grad_norm': 0.521860659122467, 'learning_rate': 9.383516483516484e-06, 'epoch': 0.06227106227106227}
Step: 89 {'loss': 0.1508, 'grad_norm': 0.56801837682724, 'learning_rate': 9.347252747252749e-06, 'epoch': 0.06593406593406594}
Step: 94 {'loss': 0.1257, 'grad_norm': 0.5347073674201965, 'learning_rate': 9.310989010989012e-06, 'epoch': 0.0695970695970696}
Step: 99 {'loss': 0.187, 'grad_norm': 0.5496135950088501, 'learning_rate': 9.274725274725277e-06, 'epoch': 0.07326007326007326}
Step: 104 {'loss': 0.1954, 'grad_norm': 0.7482754588127136, 'learning_rate': 9.23846153846154e-06, 'epoch': 0.07692307692307693}
Step: 109 {'loss': 0.1157, 'grad_norm': 0.11614499986171722, 'learning_rate': 9.202197802197803e-06, 'epoch': 0.08058608058608059}
Step: 114 {'loss': 0.1099, 'grad_norm': 0.21353064477443695, 'learning_rate': 9.165934065934066e-06, 'epoch': 0.08424908424908426}
Step: 119 {'loss': 0.1752, 'grad_norm': 0.4894441068172455, 'learning_rate': 9.12967032967033e-06, 'epoch': 0.08791208791208792}
Step: 124 {'loss': 0.1616, 'grad_norm': 0.6079414486885071, 'learning_rate': 9.093406593406593e-06, 'epoch': 0.09157509157509157}
Step: 129 {'loss': 0.1349, 'grad_norm': 0.08628781884908676, 'learning_rate': 9.057142857142858e-06, 'epoch': 0.09523809523809523}
Step: 134 {'loss': 0.1627, 'grad_norm': 0.5504783987998962, 'learning_rate': 9.020879120879121e-06, 'epoch': 0.0989010989010989}
Step: 139 {'loss': 0.1627, 'grad_norm': 1.0104156732559204, 'learning_rate': 8.984615384615386e-06, 'epoch': 0.10256410256410256}
Step: 144 {'loss': 0.111, 'grad_norm': 0.2242872714996338, 'learning_rate': 8.948351648351649e-06, 'epoch': 0.10622710622710622}
Step: 149 {'loss': 0.1287, 'grad_norm': 0.20702646672725677, 'learning_rate': 8.912087912087912e-06, 'epoch': 0.10989010989010989}
Step: 154 {'loss': 0.1564, 'grad_norm': 0.42282870411872864, 'learning_rate': 8.875824175824177e-06, 'epoch': 0.11355311355311355}
Step: 159 {'loss': 0.1234, 'grad_norm': 0.29965367913246155, 'learning_rate': 8.83956043956044e-06, 'epoch': 0.11721611721611722}
Step: 164 {'loss': 0.1386, 'grad_norm': 0.25579577684402466, 'learning_rate': 8.803296703296704e-06, 'epoch': 0.12087912087912088}
Step: 169 {'loss': 0.1429, 'grad_norm': 0.9871158599853516, 'learning_rate': 8.767032967032967e-06, 'epoch': 0.12454212454212454}
Step: 174 {'loss': 0.1491, 'grad_norm': 0.4206677973270416, 'learning_rate': 8.730769230769232e-06, 'epoch': 0.1282051282051282}
Step: 179 {'loss': 0.1145, 'grad_norm': 0.5669340491294861, 'learning_rate': 8.694505494505495e-06, 'epoch': 0.13186813186813187}
Step: 184 {'loss': 0.123, 'grad_norm': 0.1574435532093048, 'learning_rate': 8.65824175824176e-06, 'epoch': 0.13553113553113552}
Step: 189 {'loss': 0.1693, 'grad_norm': 0.5592064261436462, 'learning_rate': 8.621978021978023e-06, 'epoch': 0.1391941391941392}
Step: 194 {'loss': 0.1243, 'grad_norm': 0.5779590606689453, 'learning_rate': 8.585714285714287e-06, 'epoch': 0.14285714285714285}
Step: 199 {'loss': 0.1396, 'grad_norm': 0.11793188750743866, 'learning_rate': 8.54945054945055e-06, 'epoch': 0.14652014652014653}
Step: 204 {'loss': 0.1117, 'grad_norm': 0.5391713976860046, 'learning_rate': 8.513186813186814e-06, 'epoch': 0.15018315018315018}
Step: 209 {'loss': 0.1466, 'grad_norm': 0.921928882598877, 'learning_rate': 8.476923076923078e-06, 'epoch': 0.15384615384615385}
Step: 214 {'loss': 0.1295, 'grad_norm': 0.48140949010849, 'learning_rate': 8.440659340659341e-06, 'epoch': 0.1575091575091575}
Step: 219 {'loss': 0.1887, 'grad_norm': 0.658561646938324, 'learning_rate': 8.404395604395606e-06, 'epoch': 0.16117216117216118}
Step: 224 {'loss': 0.1308, 'grad_norm': 0.6024790406227112, 'learning_rate': 8.368131868131869e-06, 'epoch': 0.16483516483516483}
Step: 229 {'loss': 0.067, 'grad_norm': 0.24153736233711243, 'learning_rate': 8.331868131868132e-06, 'epoch': 0.1684981684981685}
Step: 234 {'loss': 0.117, 'grad_norm': 0.17423799633979797, 'learning_rate': 8.295604395604395e-06, 'epoch': 0.17216117216117216}
Step: 239 {'loss': 0.1445, 'grad_norm': 0.6188604831695557, 'learning_rate': 8.25934065934066e-06, 'epoch': 0.17582417582417584}
Step: 244 {'loss': 0.1086, 'grad_norm': 0.47320955991744995, 'learning_rate': 8.223076923076923e-06, 'epoch': 0.1794871794871795}
Step: 249 {'loss': 0.1047, 'grad_norm': 0.22519785165786743, 'learning_rate': 8.186813186813188e-06, 'epoch': 0.18315018315018314}
Step: 254 {'loss': 0.1507, 'grad_norm': 0.8073124885559082, 'learning_rate': 8.15054945054945e-06, 'epoch': 0.18681318681318682}
Step: 259 {'loss': 0.1354, 'grad_norm': 0.5822990536689758, 'learning_rate': 8.114285714285715e-06, 'epoch': 0.19047619047619047}
Step: 264 {'loss': 0.1733, 'grad_norm': 0.7305815815925598, 'learning_rate': 8.078021978021978e-06, 'epoch': 0.19413919413919414}
Step: 269 {'loss': 0.1101, 'grad_norm': 0.4647897779941559, 'learning_rate': 8.041758241758243e-06, 'epoch': 0.1978021978021978}
Step: 274 {'loss': 0.1054, 'grad_norm': 0.6543989181518555, 'learning_rate': 8.005494505494506e-06, 'epoch': 0.20146520146520147}
Step: 279 {'loss': 0.1129, 'grad_norm': 0.8039067983627319, 'learning_rate': 7.96923076923077e-06, 'epoch': 0.20512820512820512}
Step: 284 {'loss': 0.1249, 'grad_norm': 0.35283106565475464, 'learning_rate': 7.932967032967034e-06, 'epoch': 0.2087912087912088}
Step: 289 {'loss': 0.1549, 'grad_norm': 0.6537496447563171, 'learning_rate': 7.896703296703297e-06, 'epoch': 0.21245421245421245}
Step: 294 {'loss': 0.0883, 'grad_norm': 0.23383976519107819, 'learning_rate': 7.860439560439561e-06, 'epoch': 0.21611721611721613}
Step: 299 {'loss': 0.1313, 'grad_norm': 0.1237742155790329, 'learning_rate': 7.824175824175825e-06, 'epoch': 0.21978021978021978}
Step: 304 {'loss': 0.1591, 'grad_norm': 0.7631969451904297, 'learning_rate': 7.78791208791209e-06, 'epoch': 0.22344322344322345}
Step: 309 {'loss': 0.0925, 'grad_norm': 0.48745134472846985, 'learning_rate': 7.751648351648352e-06, 'epoch': 0.2271062271062271}
Step: 314 {'loss': 0.1326, 'grad_norm': 0.6884176731109619, 'learning_rate': 7.715384615384615e-06, 'epoch': 0.23076923076923078}
Step: 319 {'loss': 0.125, 'grad_norm': 0.41068509221076965, 'learning_rate': 7.679120879120878e-06, 'epoch': 0.23443223443223443}
Step: 324 {'loss': 0.1141, 'grad_norm': 1.1253948211669922, 'learning_rate': 7.642857142857143e-06, 'epoch': 0.23809523809523808}
Step: 329 {'loss': 0.1702, 'grad_norm': 0.7410513162612915, 'learning_rate': 7.606593406593405e-06, 'epoch': 0.24175824175824176}
Step: 334 {'loss': 0.1521, 'grad_norm': 0.9737598896026611, 'learning_rate': 7.57032967032967e-06, 'epoch': 0.2454212454212454}
Step: 339 {'loss': 0.137, 'grad_norm': 1.0085108280181885, 'learning_rate': 7.534065934065934e-06, 'epoch': 0.2490842490842491}
Step: 344 {'loss': 0.0966, 'grad_norm': 0.486762672662735, 'learning_rate': 7.497802197802198e-06, 'epoch': 0.25274725274725274}
Step: 349 {'loss': 0.1231, 'grad_norm': 0.801877498626709, 'learning_rate': 7.4615384615384615e-06, 'epoch': 0.2564102564102564}
Step: 354 {'loss': 0.1453, 'grad_norm': 0.6585664749145508, 'learning_rate': 7.425274725274726e-06, 'epoch': 0.2600732600732601}
Step: 359 {'loss': 0.1296, 'grad_norm': 0.2636565566062927, 'learning_rate': 7.389010989010989e-06, 'epoch': 0.26373626373626374}
Step: 364 {'loss': 0.0983, 'grad_norm': 0.25512686371803284, 'learning_rat

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "<|/code|>": 32014,
+  "<|/data|>": 32033,
+  "<|/inst|>": 32037,
+  "<|/query|>": 32031,
+  "<|/sys|>": 32035,
+  "<|assistant_mask|>": 32017,
+  "<|assistant|>": 32001,
+  "<|calc|>": 32012,
+  "<|code|>": 32013,
+  "<|continue|>": 32009,
+  "<|data|>": 32032,
+  "<|diff_marker|>": 32025,
+  "<|disc_sep|>": 32029,
+  "<|disc_start|>": 32028,
+  "<|disc_thread|><|query|>": 32030,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|fim_middle|>": 32021,
+  "<|fim_prefix|>": 32020,
+  "<|fim_suffix|>": 32022,
+  "<|function_call|>": 32005,
+  "<|function_list|>": 32011,
+  "<|function_output|>": 32003,
+  "<|ghissue|>": 32026,
+  "<|ghreview|>": 32027,
+  "<|inst|>": 32036,
+  "<|ipynb_marker|>": 32024,
+  "<|message|>": 32019,
+  "<|meta_start|>": 32023,
+  "<|raw|>": 32008,
+  "<|resource|>": 32016,
+  "<|start|>": 32018,
+  "<|step|>": 32002,
+  "<|summary|>": 32015,
+  "<|system|>": 32006,
+  "<|sys|>": 32034,
+  "<|tag|>": 32004,
+  "<|user|>": 32010
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": ".\\DigitalSoul",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 3,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "num_local_experts": 3,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.44.0"
+}

mergekit_moe_config.yml

@@ -0,0 +1,144 @@
+base_model: TroyDoesAI/BlackSheep-4B
+gate_mode: random # one of "hidden", "cheap_embed", or "random"
+
+# There are three methods for populating the MoE gates implemented.
+
+# "hidden"
+# Uses the hidden state representations of the positive/negative prompts for MoE gate parameters. Best quality and most effective option; the default. Requires evaluating each prompt using the base model so you might not be able to use this on constrained hardware (depending on the model). You can use --load-in-8bit or --load-in-4bit to reduce VRAM usage.
+
+# "cheap_embed"
+# Uses only the raw token embedding of the prompts, using the same gate parameters for every layer. Distinctly less effective than "hidden". Can be run on much, much lower end hardware.
+
+# "random"
+# Randomly initializes the MoE gates. Good for if you are going to fine tune the model afterwards, or maybe if you want something a little unhinged? I won't judge.
+
+experts:
+  - source_model: TroyDoesAI/BlackSheep-4B
+    positive_prompts:
+    - "digital"
+    - "soul"
+    - "<|assistant|>"
+    - "instruction"
+    - "input"
+    - "output"
+    - "response"
+    - "story"
+    - "stories"
+    - "creative"
+    - "curious"
+    - "action"
+    - "sensitive"
+    - "pleasant"
+    - "thoughtful"
+    - "interesting"
+    - "BEGININPUT"
+    - "BEGINCONTEXT"
+    - "ENDCONTEXT"
+    - "ENDINPUT"
+    - "BEGININSTRUCTION"
+    - "ENDINSTRUCTION"
+    - "url"
+    - "date"
+    - "source"
+    - "context"
+    - "cite"
+    - "mermaid"
+    - "flow"
+    - "diagram"
+    - "sequence"
+    - "series"
+    - "code to flow"
+    - "code to diagram"
+    - "python to flow diagram"
+    - "program to flow"
+    - "program to flow diagram"
+    - "write"
+    - "create"
+    - "visualize"
+    - "show"
+    - "explain"
+    - "draw"
+    - "describe"
+    - "summarize"
+    - "concise"
+    - "do"
+    - "say"
+    - "code"
+    - "```"
+    - "```mermaid"
+    - "graphTB"
+    - "graphTD"
+    - "graphLR"
+    - "graphRL"
+
+  - source_model: TroyDoesAI/BlackSheep-4B
+    positive_prompts:
+    - "Digital Soul"
+    - "hello"
+    - "you"
+    - "assistant"
+    - "who"
+    - "what"
+    - "when"
+    - "where"
+    - "why"
+    - "how"
+    - "me"
+    - "politic"
+    - "conservative"
+
+  - source_model: TroyDoesAI/BlackSheep-4B
+    positive_prompts:
+    - "<|assistant|>"
+    - "instruction"
+    - "input"
+    - "output"
+    - "response"
+    - "story"
+    - "stories"
+    - "creative"
+    - "curious"
+    - "action"
+    - "sensitive"
+    - "pleasant"
+    - "thoughtful"
+    - "interesting"
+    - "BEGININPUT"
+    - "BEGINCONTEXT"
+    - "ENDCONTEXT"
+    - "ENDINPUT"
+    - "BEGININSTRUCTION"
+    - "ENDINSTRUCTION"
+    - "url"
+    - "date"
+    - "source"
+    - "context"
+    - "cite"
+    - "mermaid"
+    - "flow"
+    - "diagram"
+    - "sequence"
+    - "series"
+    - "code to flow"
+    - "code to diagram"
+    - "python to flow diagram"
+    - "program to flow"
+    - "program to flow diagram"
+    - "write"
+    - "create"
+    - "visualize"
+    - "show"
+    - "explain"
+    - "draw"
+    - "describe"
+    - "summarize"
+    - "concise"
+    - "do"
+    - "say"
+    - "code"
+    - "```"
+    - "```mermaid"
+    - "graphTB"
+    - "graphTD"
+    - "graphLR"
+    - "graphRL"

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a2c5bfcab4531a259160d621b362de1c05578ccda88e986b34be7c2ac40a56
+size 4991420771

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71573bdbe775a26e3ad9cbf9ecd51032f0307af9c8f96bdfc3f19d0624d73c4
+size 4995766167

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948697ccb8053a18f248fa57e188ea3b80e4fc34d03ed1814efb7024602f740b
+size 4957997958

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d349868422cd99a07e86708db413472ce5932a6b0a83f2589b92f4d3905d64dd
+size 2361428548

pytorch_model.bin.index.json

@@ -0,0 +1,522 @@
+{
+  "metadata": {
+    "total_size": 17306425344
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|/inst|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": true,
+    "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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,350 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|step|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|function_output|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|function_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|raw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|continue|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<|function_list|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<|calc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<|code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<|/code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<|summary|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<|resource|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<|assistant_mask|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<|meta_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<|ipynb_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<|diff_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<|ghissue|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<|ghreview|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<|disc_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<|disc_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<|disc_thread|><|query|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<|/query|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<|data|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<|/data|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<|sys|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<|/sys|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<|inst|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<|/inst|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|/inst|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}