Upload folder using huggingface_hub

config.json

@@ -0,0 +1,80 @@
+{
+  "architectures": [
+    "MistralForCausalLM",
+    "MistralAIDetectorForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_dropout": 0.1,
+  "detr_config": {
+    "aux_loss": true,
+    "center_noise_scale": 0.6,
+    "dab_detr": true,
+    "dec_layers": 3,
+    "dn_detr": true,
+    "enc_layers": 3,
+    "eos_coef": 0.1,
+    "extractor_dtype": "bfloat16",
+    "giou_loss_coef": 1.0,
+    "label_loss_coef": 2.0,
+    "losses": [],
+    "model_dim": 256,
+    "n_input_proj": 2,
+    "nheads": 8,
+    "noise_offset": 0.05,
+    "num_groups": 5,
+    "num_input_proj_layers": 2,
+    "num_queries": 45,
+    "position_embedding": "sine",
+    "proj_dropout": 0.5,
+    "query_initialization_method": "default",
+    "set_cost_class": 2,
+    "set_cost_giou": 1,
+    "set_cost_iou": 2,
+    "set_cost_reference": 1,
+    "set_cost_span": 5,
+    "span_loss_coef": 10.0,
+    "span_loss_type": "l1",
+    "special_ref_points": true,
+    "temperature": 10000,
+    "tgt_label_loss_coef": 0.0,
+    "tgt_loss_giou_coef": 3.0,
+    "tgt_loss_span_coef": 9.0,
+    "use_focal_loss": true,
+    "width_noise_scale": 0.7
+  },
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "ai",
+    "1": "human",
+    "2": "mixed"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 1024,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretrained_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "trained_classification_head": false,
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 32768,
+  "with_detr": true
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7de8eb9bd554cccc999649fd5a3a28a44d09042879d6c1cedd13f59c86f7a8
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a5f871a0fbb7919f263d78caff0d4d3b7a1d444552db3011ada70f48fd5ee4
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c201613d10850ba714fc1c38282f064794a36b8a084b3291e223f055a48431e
+size 4310291500

model.safetensors.index.json

@@ -0,0 +1,483 @@
+{
+  "metadata": {
+    "total_parameters": 7121780061,
+    "total_size": 14259508604
+  },
+  "weight_map": {
+    "criterion.empty_weight": "model-00003-of-00003.safetensors",
+    "detr.class_embed.bias": "model-00003-of-00003.safetensors",
+    "detr.class_embed.weight": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.0.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.0.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.0.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.0.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.1.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.1.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.1.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.input_proj.layers.1.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.bbox_embed.layers.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.bbox_embed.layers.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.bbox_embed.layers.1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.bbox_embed.layers.1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.bbox_embed.layers.2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.bbox_embed.layers.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_kcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_kcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_kpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_kpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_qcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_qcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_qpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_qpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_qpos_sine_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_qpos_sine_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_v_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.ca_v_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.cross_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.cross_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.linear1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.linear1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.linear2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.linear2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.norm1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.norm1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.norm2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.norm2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.norm3.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.norm3.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_kcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_kcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_kpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_kpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_qcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_qcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_qpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_qpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_v_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.sa_v_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_kcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_kcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_kpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_kpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_qcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_qcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_qpos_sine_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_qpos_sine_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_v_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.ca_v_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.cross_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.cross_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.linear1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.linear1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.linear2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.linear2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.norm1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.norm1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.norm2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.norm2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.norm3.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.norm3.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_kcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_kcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_kpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_kpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_qcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_qcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_qpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_qpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_v_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.sa_v_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_kcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_kcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_kpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_kpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_qcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_qcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_qpos_sine_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_qpos_sine_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_v_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.ca_v_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.cross_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.cross_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.linear1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.linear1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.linear2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.linear2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.norm1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.norm1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.norm2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.norm2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.norm3.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.norm3.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_kcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_kcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_kpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_kpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_qcontent_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_qcontent_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_qpos_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_qpos_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_v_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.sa_v_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.norm.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.norm.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.0.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.0.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.0.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.0.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.1.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.1.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.1.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.query_scale.layers.1.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.0.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.0.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.0.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.0.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.1.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.1.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.1.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_anchor_head.layers.1.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.0.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.0.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.0.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.0.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.1.mapper.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.1.mapper.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.1.mapper.2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.decoder.ref_point_head.layers.1.mapper.2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.ffn.mapping.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.ffn.mapping.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.ffn.mapping.3.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.ffn.mapping.3.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.norm1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.norm1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.norm2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.norm2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.self_attn.in_proj_bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.self_attn.in_proj_weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.ffn.mapping.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.ffn.mapping.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.ffn.mapping.3.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.ffn.mapping.3.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.norm1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.norm1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.norm2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.norm2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.self_attn.in_proj_bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.self_attn.in_proj_weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.ffn.mapping.0.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.ffn.mapping.0.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.ffn.mapping.3.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.ffn.mapping.3.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.norm1.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.norm1.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.norm2.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.norm2.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.self_attn.in_proj_bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.self_attn.in_proj_weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "detr.transformer.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.label_enc.weight": "model-00003-of-00003.safetensors",
+    "detr.transformer.query_embed.query_embed.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404