End of training

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: HachiML/Mists-7B-v01-not-trained
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Mists-7B-v01-projector-trained
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/siseikatu8/huggingface/runs/2vf2q5nm)
+# Mists-7B-v01-projector-trained
+
+This model is a fine-tuned version of [HachiML/Mists-7B-v01-not-trained](https://huggingface.co/HachiML/Mists-7B-v01-not-trained) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5989
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.8704        | 0.0526 | 2000  | 0.7797          |
+| 0.7321        | 0.1051 | 4000  | 0.7205          |
+| 0.7002        | 0.1577 | 6000  | 0.6992          |
+| 0.6735        | 0.2102 | 8000  | 0.6755          |
+| 0.6644        | 0.2628 | 10000 | 0.6625          |
+| 0.6562        | 0.3153 | 12000 | 0.6539          |
+| 0.6512        | 0.3679 | 14000 | 0.6473          |
+| 0.638         | 0.4205 | 16000 | 0.6394          |
+| 0.6266        | 0.4730 | 18000 | 0.6325          |
+| 0.627         | 0.5256 | 20000 | 0.6278          |
+| 0.6215        | 0.5781 | 22000 | 0.6241          |
+| 0.6192        | 0.6307 | 24000 | 0.6199          |
+| 0.6127        | 0.6832 | 26000 | 0.6163          |
+| 0.6121        | 0.7358 | 28000 | 0.6131          |
+| 0.6078        | 0.7884 | 30000 | 0.6089          |
+| 0.5986        | 0.8409 | 32000 | 0.6058          |
+| 0.6011        | 0.8935 | 34000 | 0.6027          |
+| 0.5934        | 0.9460 | 36000 | 0.6005          |
+| 0.589         | 0.9986 | 38000 | 0.5989          |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<pad>": 32769,
+  "<time_series>": 32768
+}

config.json

@@ -0,0 +1,127 @@
+{
+  "_name_or_path": "HachiML/Mists-7B-v01-not-trained",
+  "architectures": [
+    "MistsForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "HachiML/Mists-7B-v01-not-trained--configuration_mists.MistsConfig",
+    "AutoModel": "HachiML/Mists-7B-v01-not-trained--modeling_mists.MistsForConditionalGeneration"
+  },
+  "ignore_index": -100,
+  "model_type": "mists",
+  "pad_token_id": 32769,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32832
+  },
+  "time_series_config": {
+    "_name_or_path": "HachiML/MOMENT-1-large-embedding-v0.1",
+    "architectures": [
+      "MomentEmbeddingModel"
+    ],
+    "auto_map": {
+      "AutoConfig": "HachiML/MOMENT-1-large-embedding-v0.1--configuration_moment.MomentConfig",
+      "AutoModel": "HachiML/MOMENT-1-large-embedding-v0.1--modeling_moment.MomentEmbeddingModel"
+    },
+    "mask_ratio": 0.0,
+    "model_type": "moment",
+    "patch_len": 8,
+    "patch_stride_len": 8,
+    "revin_affine": false,
+    "t5_config": {
+      "add_cross_attention": false,
+      "attn_implementation": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "classifier_dropout": 0.0,
+      "cross_attention_hidden_size": null,
+      "d_ff": 2816,
+      "d_kv": 64,
+      "d_model": 1024,
+      "decoder_start_token_id": 0,
+      "dense_act_fn": "gelu_new",
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout_rate": 0.1,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": 1,
+      "exponential_decay_length_penalty": null,
+      "feed_forward_proj": "gated-gelu",
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_factor": 1.0,
+      "is_decoder": false,
+      "is_encoder_decoder": true,
+      "is_gated_act": true,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_epsilon": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "n_positions": 512,
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_decoder_layers": 24,
+      "num_heads": 16,
+      "num_layers": 24,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_past": true,
+      "output_scores": false,
+      "pad_token_id": 0,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "relative_attention_max_distance": 128,
+      "relative_attention_num_buckets": 32,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "vocab_size": 32128
+    },
+    "torch_dtype": "float32"
+  },
+  "time_series_hidden_size": 1024,
+  "time_series_token_index": 32768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32769,
+  "transformers_version": "4.42.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b49a3d2bd1b04cc6aa834fb077a0815db15be6e1a0e98258ef35b7edb162f27
+size 4993259168

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3bab7edc4bcc79cbe39a10c20db63a9743de67f5b2ae20934f24f7f4d013c07
+size 4915917648

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d1a0c0ebd87c4f813b96ce28fe6228aa22ae8a00d11319c7e756fed3aa20bd
+size 4999820928

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5bbbcf5b99a8257a7f7a49d21f3ecdaa38ec02bbdfd8d4dcbc79a80c878516
+size 1057531920

model.safetensors.index.json

@@ -0,0 +1,525 @@
+{
+  "metadata": {
+    "total_size": 15966459904
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.mask_embedding": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.encoder.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "time_series_tower.patch_embedding.mask_embedding": "model-00001-of-00004.safetensors",
+    "time_series_tower.patch_embedding.position_embedding.pe": "model-00001-of-00004.safetensors",
+    "time_series_tower.patch_embedding.value_embedding.weight": "model-00001-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3fd10f3596ce1115521a5c8ae4ad41f7b1bfe32079fda5c11551f69dd4c14d
+size 5368