chore: move tokenizer.json to Git LFS

added_tokens.json

@@ -1,127 +1,3 @@
-{
-  "<|assistant|>": 219402,
-  "<|beginoftext|>": 219396,
-  "<|dummy_id_100|>": 219505,
-  "<|dummy_id_101|>": 219506,
-  "<|dummy_id_102|>": 219507,
-  "<|dummy_id_103|>": 219508,
-  "<|dummy_id_104|>": 219509,
-  "<|dummy_id_105|>": 219510,
-  "<|dummy_id_106|>": 219511,
-  "<|dummy_id_107|>": 219512,
-  "<|dummy_id_108|>": 219513,
-  "<|dummy_id_109|>": 219514,
-  "<|dummy_id_10|>": 219414,
-  "<|dummy_id_110|>": 219515,
-  "<|dummy_id_111|>": 219516,
-  "<|dummy_id_112|>": 219517,
-  "<|dummy_id_113|>": 219518,
-  "<|dummy_id_114|>": 219519,
-  "<|dummy_id_11|>": 219415,
-  "<|dummy_id_12|>": 219417,
-  "<|dummy_id_13|>": 219418,
-  "<|dummy_id_14|>": 219419,
-  "<|dummy_id_15|>": 219420,
-  "<|dummy_id_16|>": 219421,
-  "<|dummy_id_17|>": 219422,
-  "<|dummy_id_18|>": 219423,
-  "<|dummy_id_19|>": 219424,
-  "<|dummy_id_1|>": 219404,
-  "<|dummy_id_20|>": 219425,
-  "<|dummy_id_21|>": 219426,
-  "<|dummy_id_22|>": 219427,
-  "<|dummy_id_23|>": 219428,
-  "<|dummy_id_24|>": 219429,
-  "<|dummy_id_25|>": 219430,
-  "<|dummy_id_26|>": 219431,
-  "<|dummy_id_27|>": 219432,
-  "<|dummy_id_28|>": 219433,
-  "<|dummy_id_29|>": 219434,
-  "<|dummy_id_2|>": 219406,
-  "<|dummy_id_30|>": 219435,
-  "<|dummy_id_31|>": 219436,
-  "<|dummy_id_32|>": 219437,
-  "<|dummy_id_33|>": 219438,
-  "<|dummy_id_34|>": 219439,
-  "<|dummy_id_35|>": 219440,
-  "<|dummy_id_36|>": 219441,
-  "<|dummy_id_37|>": 219442,
-  "<|dummy_id_38|>": 219443,
-  "<|dummy_id_39|>": 219444,
-  "<|dummy_id_3|>": 219407,
-  "<|dummy_id_40|>": 219445,
-  "<|dummy_id_41|>": 219446,
-  "<|dummy_id_42|>": 219447,
-  "<|dummy_id_43|>": 219448,
-  "<|dummy_id_44|>": 219449,
-  "<|dummy_id_45|>": 219450,
-  "<|dummy_id_46|>": 219451,
-  "<|dummy_id_47|>": 219452,
-  "<|dummy_id_48|>": 219453,
-  "<|dummy_id_49|>": 219454,
-  "<|dummy_id_4|>": 219408,
-  "<|dummy_id_50|>": 219455,
-  "<|dummy_id_51|>": 219456,
-  "<|dummy_id_52|>": 219457,
-  "<|dummy_id_53|>": 219458,
-  "<|dummy_id_54|>": 219459,
-  "<|dummy_id_55|>": 219460,
-  "<|dummy_id_56|>": 219461,
-  "<|dummy_id_57|>": 219462,
-  "<|dummy_id_58|>": 219463,
-  "<|dummy_id_59|>": 219464,
-  "<|dummy_id_5|>": 219409,
-  "<|dummy_id_60|>": 219465,
-  "<|dummy_id_61|>": 219466,
-  "<|dummy_id_62|>": 219467,
-  "<|dummy_id_63|>": 219468,
-  "<|dummy_id_64|>": 219469,
-  "<|dummy_id_65|>": 219470,
-  "<|dummy_id_66|>": 219471,
-  "<|dummy_id_67|>": 219472,
-  "<|dummy_id_68|>": 219473,
-  "<|dummy_id_69|>": 219474,
-  "<|dummy_id_6|>": 219410,
-  "<|dummy_id_70|>": 219475,
-  "<|dummy_id_71|>": 219476,
-  "<|dummy_id_72|>": 219477,
-  "<|dummy_id_73|>": 219478,
-  "<|dummy_id_74|>": 219479,
-  "<|dummy_id_75|>": 219480,
-  "<|dummy_id_76|>": 219481,
-  "<|dummy_id_77|>": 219482,
-  "<|dummy_id_78|>": 219483,
-  "<|dummy_id_79|>": 219484,
-  "<|dummy_id_7|>": 219411,
-  "<|dummy_id_80|>": 219485,
-  "<|dummy_id_81|>": 219486,
-  "<|dummy_id_82|>": 219487,
-  "<|dummy_id_83|>": 219488,
-  "<|dummy_id_84|>": 219489,
-  "<|dummy_id_85|>": 219490,
-  "<|dummy_id_86|>": 219491,
-  "<|dummy_id_87|>": 219492,
-  "<|dummy_id_88|>": 219493,
-  "<|dummy_id_89|>": 219494,
-  "<|dummy_id_8|>": 219412,
-  "<|dummy_id_90|>": 219495,
-  "<|dummy_id_91|>": 219496,
-  "<|dummy_id_92|>": 219497,
-  "<|dummy_id_93|>": 219498,
-  "<|dummy_id_94|>": 219499,
-  "<|dummy_id_95|>": 219500,
-  "<|dummy_id_96|>": 219501,
-  "<|dummy_id_97|>": 219502,
-  "<|dummy_id_98|>": 219503,
-  "<|dummy_id_99|>": 219504,
-  "<|dummy_id_9|>": 219413,
-  "<|endofprompt|>": 219416,
-  "<|endoftext|>": 219395,
-  "<|endofturn|>": 219405,
-  "<|fim_middle|>": 219398,
-  "<|fim_prefix|>": 219397,
-  "<|fim_suffix|>": 219399,
-  "<|startofturn|>": 219403,
-  "<|system|>": 219400,
-  "<|user|>": 219401
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05a306675ad166e4dac028aef341098336f67e4342faeea5190a60364b20557
+size 3613

config.json

@@ -1,47 +1,3 @@
-{
-  "absolute_position_embedding": false,
-  "architectures": [
-    "MotifForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "attn_rms_norm_eps": 1e-05,
-  "auto_map": {
-    "AutoConfig": "configuration_motif.MotifConfig",
-    "AutoModelForCausalLM": "modeling_motif.MotifForCausalLM"
-  },
-  "bfloat16": true,
-  "bos_token_id": 219396,
-  "decoder_split_layers": [],
-  "encoder_split_layers": [],
-  "eos_token_id": 219395,
-  "expanded": true,
-  "fused_rope": false,
-  "head_dim": 128,
-  "hidden_act": "poly_norm",
-  "hidden_size": 4096,
-  "initializer_range": 2e-05,
-  "intermediate_size": 16384,
-  "load_pretrained": null,
-  "loss_reduction": "mean",
-  "max_position_embeddings": 32768,
-  "max_window_layers": 28,
-  "model_type": "Motif",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 16,
-  "num_noise_heads": 8,
-  "k_ratio": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0",
-  "use_bias": false,
-  "use_cache": true,
-  "use_moreh_attention": false,
-  "use_pipeline": false,
-  "use_sliding_window": false,
-  "vocab_size": 219520
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:1143d3359cb00644df12fcb6de9f4c722269d513d0028f8def6e32d1c7f6b567
+size 1212

generation_config.json

@@ -1,7 +1,3 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 219396,
-  "eos_token_id": 219395,
-  "transformers_version": "4.56.2",
-  "use_cache": false
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58c5b895423d1e2150b55643de984f93ed24bca4bf9266cc0583795414cc1ac
+size 143

model.safetensors.index.json

@@ -1,651 +1,3 @@
-{
-  "metadata": {
-    "total_parameters": 12703860896,
-    "total_size": 50815443584
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00011-of-00011.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.act_fn.bias": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.act_fn.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.lambda_k1": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.lambda_k2": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.lambda_q1": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.lambda_q2": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.subln.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.act_fn.bias": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.act_fn.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.lambda_k1": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.lambda_k2": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.lambda_q1": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.lambda_q2": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.subln.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.10.mlp.act_fn.bias": "model-00004-of-00011.safetensors",
-    "model.layers.10.mlp.act_fn.weight": "model-00004-of-00011.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.lambda_k1": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.lambda_k2": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.lambda_q1": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.lambda_q2": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.subln.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.act_fn.bias": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.act_fn.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.lambda_k1": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.lambda_k2": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.lambda_q1": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.lambda_q2": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.subln.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.act_fn.bias": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.act_fn.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.lambda_k1": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.lambda_k2": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.lambda_q1": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.lambda_q2": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.subln.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.act_fn.bias": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.act_fn.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.lambda_k1": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.lambda_k2": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.lambda_q1": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.lambda_q2": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.subln.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.14.mlp.act_fn.bias": "model-00005-of-00011.safetensors",
-    "model.layers.14.mlp.act_fn.weight": "model-00005-of-00011.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.lambda_k1": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.lambda_k2": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.lambda_q1": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.lambda_q2": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.subln.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.act_fn.bias": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.act_fn.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.lambda_k1": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.lambda_k2": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.lambda_q1": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.lambda_q2": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.subln.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.act_fn.bias": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.act_fn.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.lambda_k1": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.lambda_k2": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.lambda_q1": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.lambda_q2": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.subln.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.act_fn.bias": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.act_fn.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.lambda_k1": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.lambda_k2": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.lambda_q1": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.lambda_q2": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.subln.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.act_fn.bias": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.act_fn.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.lambda_k1": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.lambda_k2": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.lambda_q1": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.lambda_q2": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.subln.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.act_fn.bias": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.act_fn.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.lambda_k1": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.lambda_k2": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.lambda_q1": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.lambda_q2": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.subln.weight": "model-00005-of-00011.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.act_fn.bias": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.act_fn.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.lambda_k1": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.lambda_k2": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.lambda_q1": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.lambda_q2": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.subln.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.act_fn.bias": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.act_fn.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.lambda_k1": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.lambda_k2": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.lambda_q1": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.lambda_q2": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.subln.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.act_fn.bias": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.act_fn.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.lambda_k1": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.lambda_k2": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.lambda_q1": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.lambda_q2": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.subln.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.mlp.act_fn.bias": "model-00006-of-00011.safetensors",
-    "model.layers.22.mlp.act_fn.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.lambda_k1": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.lambda_k2": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.lambda_q1": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.lambda_q2": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.subln.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.mlp.act_fn.bias": "model-00007-of-00011.safetensors",
-    "model.layers.23.mlp.act_fn.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.lambda_k1": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.lambda_k2": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.lambda_q1": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.lambda_q2": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.subln.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.act_fn.bias": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.act_fn.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.lambda_k1": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.lambda_k2": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.lambda_q1": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.lambda_q2": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.subln.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.act_fn.bias": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.act_fn.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.lambda_k1": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.lambda_k2": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.lambda_q1": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.lambda_q2": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.subln.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.mlp.act_fn.bias": "model-00007-of-00011.safetensors",
-    "model.layers.26.mlp.act_fn.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.lambda_k1": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.lambda_k2": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.lambda_q1": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.lambda_q2": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.subln.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.mlp.act_fn.bias": "model-00007-of-00011.safetensors",
-    "model.layers.27.mlp.act_fn.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.lambda_k1": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.lambda_k2": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.lambda_q1": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.lambda_q2": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.subln.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.act_fn.bias": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.act_fn.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.lambda_k1": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.lambda_k2": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.lambda_q1": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.lambda_q2": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.subln.weight": "model-00007-of-00011.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.act_fn.bias": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.act_fn.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.lambda_k1": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.lambda_k2": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.lambda_q1": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.lambda_q2": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.subln.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.act_fn.bias": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.act_fn.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.lambda_k1": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.lambda_k2": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.lambda_q1": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.lambda_q2": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.subln.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.mlp.act_fn.bias": "model-00008-of-00011.safetensors",
-    "model.layers.30.mlp.act_fn.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.lambda_k1": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.lambda_k2": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.lambda_q1": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.lambda_q2": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.subln.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.mlp.act_fn.bias": "model-00008-of-00011.safetensors",
-    "model.layers.31.mlp.act_fn.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.lambda_k1": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.lambda_k2": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.lambda_q1": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.lambda_q2": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.subln.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.mlp.act_fn.bias": "model-00009-of-00011.safetensors",
-    "model.layers.32.mlp.act_fn.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.lambda_k1": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.lambda_k2": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.lambda_q1": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.lambda_q2": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.subln.weight": "model-00008-of-00011.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.act_fn.bias": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.act_fn.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.lambda_k1": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.lambda_k2": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.lambda_q1": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.lambda_q2": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.subln.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.mlp.act_fn.bias": "model-00009-of-00011.safetensors",
-    "model.layers.34.mlp.act_fn.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.lambda_k1": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.lambda_k2": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.lambda_q1": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.lambda_q2": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.subln.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.mlp.act_fn.bias": "model-00009-of-00011.safetensors",
-    "model.layers.35.mlp.act_fn.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.lambda_k1": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.lambda_k2": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.lambda_q1": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.lambda_q2": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.subln.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.mlp.act_fn.bias": "model-00009-of-00011.safetensors",
-    "model.layers.36.mlp.act_fn.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.lambda_k1": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.lambda_k2": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.lambda_q1": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.lambda_q2": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.subln.weight": "model-00009-of-00011.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.act_fn.bias": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.act_fn.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.lambda_k1": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.lambda_k2": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.lambda_q1": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.lambda_q2": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.subln.weight": "model-00009-of-00011.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.mlp.act_fn.bias": "model-00010-of-00011.safetensors",
-    "model.layers.38.mlp.act_fn.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.lambda_k1": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.lambda_k2": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.lambda_q1": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.lambda_q2": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.subln.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.mlp.act_fn.bias": "model-00010-of-00011.safetensors",
-    "model.layers.39.mlp.act_fn.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.lambda_k1": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.lambda_k2": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.lambda_q1": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.lambda_q2": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.subln.weight": "model-00010-of-00011.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.act_fn.bias": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.act_fn.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.lambda_k1": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.lambda_k2": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.lambda_q1": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.lambda_q2": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.subln.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.5.mlp.act_fn.bias": "model-00003-of-00011.safetensors",
-    "model.layers.5.mlp.act_fn.weight": "model-00003-of-00011.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.lambda_k1": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.lambda_k2": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.lambda_q1": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.lambda_q2": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.subln.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.mlp.act_fn.bias": "model-00003-of-00011.safetensors",
-    "model.layers.6.mlp.act_fn.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.lambda_k1": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.lambda_k2": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.lambda_q1": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.lambda_q2": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.subln.weight": "model-00003-of-00011.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.act_fn.bias": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.act_fn.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.lambda_k1": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.lambda_k2": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.lambda_q1": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.lambda_q2": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.subln.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.act_fn.bias": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.act_fn.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.lambda_k1": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.lambda_k2": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.lambda_q1": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.lambda_q2": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.subln.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.act_fn.bias": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.act_fn.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.lambda_k1": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.lambda_k2": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.lambda_q1": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.lambda_q2": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.subln.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.norm.weight": "model-00010-of-00011.safetensors"
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:048fe8d6ece61bc9117996335ca87995e0723042a8523eee4ba628e99e1e9490
+size 51861

special_tokens_map.json

@@ -1,23 +1,3 @@
-{
-  "bos_token": {
-    "content": "<|beginoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c38bf8642822348775b112246cc21b94d4e60d813d06f67db6e5ec7c26e3793
+size 443

tokenizer_config.json

@@ -1,1026 +1,3 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "219395": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219396": {
-      "content": "<|beginoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219397": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219398": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219399": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219400": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219401": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219402": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219403": {
-      "content": "<|startofturn|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219404": {
-      "content": "<|dummy_id_1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219405": {
-      "content": "<|endofturn|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219406": {
-      "content": "<|dummy_id_2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219407": {
-      "content": "<|dummy_id_3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219408": {
-      "content": "<|dummy_id_4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219409": {
-      "content": "<|dummy_id_5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219410": {
-      "content": "<|dummy_id_6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219411": {
-      "content": "<|dummy_id_7|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219412": {
-      "content": "<|dummy_id_8|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219413": {
-      "content": "<|dummy_id_9|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219414": {
-      "content": "<|dummy_id_10|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219415": {
-      "content": "<|dummy_id_11|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219416": {
-      "content": "<|endofprompt|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219417": {
-      "content": "<|dummy_id_12|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219418": {
-      "content": "<|dummy_id_13|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219419": {
-      "content": "<|dummy_id_14|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219420": {
-      "content": "<|dummy_id_15|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219421": {
-      "content": "<|dummy_id_16|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219422": {
-      "content": "<|dummy_id_17|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219423": {
-      "content": "<|dummy_id_18|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219424": {
-      "content": "<|dummy_id_19|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219425": {
-      "content": "<|dummy_id_20|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219426": {
-      "content": "<|dummy_id_21|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219427": {
-      "content": "<|dummy_id_22|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219428": {
-      "content": "<|dummy_id_23|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219429": {
-      "content": "<|dummy_id_24|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219430": {
-      "content": "<|dummy_id_25|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219431": {
-      "content": "<|dummy_id_26|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219432": {
-      "content": "<|dummy_id_27|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219433": {
-      "content": "<|dummy_id_28|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219434": {
-      "content": "<|dummy_id_29|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219435": {
-      "content": "<|dummy_id_30|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219436": {
-      "content": "<|dummy_id_31|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219437": {
-      "content": "<|dummy_id_32|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219438": {
-      "content": "<|dummy_id_33|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219439": {
-      "content": "<|dummy_id_34|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219440": {
-      "content": "<|dummy_id_35|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219441": {
-      "content": "<|dummy_id_36|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219442": {
-      "content": "<|dummy_id_37|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219443": {
-      "content": "<|dummy_id_38|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219444": {
-      "content": "<|dummy_id_39|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219445": {
-      "content": "<|dummy_id_40|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219446": {
-      "content": "<|dummy_id_41|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219447": {
-      "content": "<|dummy_id_42|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219448": {
-      "content": "<|dummy_id_43|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219449": {
-      "content": "<|dummy_id_44|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219450": {
-      "content": "<|dummy_id_45|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219451": {
-      "content": "<|dummy_id_46|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219452": {
-      "content": "<|dummy_id_47|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219453": {
-      "content": "<|dummy_id_48|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219454": {
-      "content": "<|dummy_id_49|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219455": {
-      "content": "<|dummy_id_50|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219456": {
-      "content": "<|dummy_id_51|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219457": {
-      "content": "<|dummy_id_52|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219458": {
-      "content": "<|dummy_id_53|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219459": {
-      "content": "<|dummy_id_54|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219460": {
-      "content": "<|dummy_id_55|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219461": {
-      "content": "<|dummy_id_56|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219462": {
-      "content": "<|dummy_id_57|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219463": {
-      "content": "<|dummy_id_58|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219464": {
-      "content": "<|dummy_id_59|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219465": {
-      "content": "<|dummy_id_60|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219466": {
-      "content": "<|dummy_id_61|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219467": {
-      "content": "<|dummy_id_62|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219468": {
-      "content": "<|dummy_id_63|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219469": {
-      "content": "<|dummy_id_64|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219470": {
-      "content": "<|dummy_id_65|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219471": {
-      "content": "<|dummy_id_66|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219472": {
-      "content": "<|dummy_id_67|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219473": {
-      "content": "<|dummy_id_68|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219474": {
-      "content": "<|dummy_id_69|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219475": {
-      "content": "<|dummy_id_70|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219476": {
-      "content": "<|dummy_id_71|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219477": {
-      "content": "<|dummy_id_72|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219478": {
-      "content": "<|dummy_id_73|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219479": {
-      "content": "<|dummy_id_74|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219480": {
-      "content": "<|dummy_id_75|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219481": {
-      "content": "<|dummy_id_76|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219482": {
-      "content": "<|dummy_id_77|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219483": {
-      "content": "<|dummy_id_78|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219484": {
-      "content": "<|dummy_id_79|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219485": {
-      "content": "<|dummy_id_80|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219486": {
-      "content": "<|dummy_id_81|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219487": {
-      "content": "<|dummy_id_82|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219488": {
-      "content": "<|dummy_id_83|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219489": {
-      "content": "<|dummy_id_84|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219490": {
-      "content": "<|dummy_id_85|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219491": {
-      "content": "<|dummy_id_86|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219492": {
-      "content": "<|dummy_id_87|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219493": {
-      "content": "<|dummy_id_88|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219494": {
-      "content": "<|dummy_id_89|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219495": {
-      "content": "<|dummy_id_90|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219496": {
-      "content": "<|dummy_id_91|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219497": {
-      "content": "<|dummy_id_92|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219498": {
-      "content": "<|dummy_id_93|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219499": {
-      "content": "<|dummy_id_94|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219500": {
-      "content": "<|dummy_id_95|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219501": {
-      "content": "<|dummy_id_96|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219502": {
-      "content": "<|dummy_id_97|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219503": {
-      "content": "<|dummy_id_98|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219504": {
-      "content": "<|dummy_id_99|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219505": {
-      "content": "<|dummy_id_100|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219506": {
-      "content": "<|dummy_id_101|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219507": {
-      "content": "<|dummy_id_102|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219508": {
-      "content": "<|dummy_id_103|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219509": {
-      "content": "<|dummy_id_104|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219510": {
-      "content": "<|dummy_id_105|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219511": {
-      "content": "<|dummy_id_106|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219512": {
-      "content": "<|dummy_id_107|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219513": {
-      "content": "<|dummy_id_108|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219514": {
-      "content": "<|dummy_id_109|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219515": {
-      "content": "<|dummy_id_110|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219516": {
-      "content": "<|dummy_id_111|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219517": {
-      "content": "<|dummy_id_112|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219518": {
-      "content": "<|dummy_id_113|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "219519": {
-      "content": "<|dummy_id_114|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "block_size": 2048,
-  "bos_token": "<|beginoftext|>",
-  "chat_template": "",
-  "clean_up_tokenization_spaces": false,
-  "corruption_rate": 0.15,
-  "default_system_prompt": "",
-  "eos_token": "<|endoftext|>",
-  "extra_ids": 0,
-  "fixed_vocab": true,
-  "merges_file_path": "./data/merges.txt",
-  "model_max_length": 1000000000000000019884624838656,
-  "padding_side": "left",
-  "seq_length": 4096,
-  "tokenizer_class": "GPT2Tokenizer",
-  "tokenizer_name": "./_motif_scripts/motif_tokenizer",
-  "tokens": -1,
-  "unk_token": "<|endoftext|>",
-  "update_tokenizer": true,
-  "use_moreh_tokenizer": false,
-  "vocab_file_path": "./data/vocab.json",
-  "vocab_size": 219395
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3faf5eb4188ed8666115e95eeae1cdd80980039ee8387c5f6bf13eaa732bc9
+size 23464