Training in progress, epoch 1

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "yanolja/EEVE-Korean-Instruct-10.8B-v1.0",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": false,
+  "vocab_size": 40960
+}

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 4096,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/README.md

@@ -0,0 +1,127 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 4096 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 1167 with parameters:
+```
+{'batch_size': 1, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 1000,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 117,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 4096, 'do_lower_case': False}) with Transformer model: LlamaModel 
+  (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "eunyounglee/EEVE-LLM2Vec-MNTP-1",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "vocab_size": 40960
+}

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.40.1",
+    "pytorch": "2.2.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,3 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,1000,0.7965733680912759,0.7679724783409906,0.7066661378875286,0.705736764400125,0.7051242959401975,0.6945454417834422,0.7249625237666293,0.7184658260023061
+0,-1,0.8034098534276466,0.7782667865494661,0.7126366714219035,0.7074880782447204,0.7115308554148531,0.7045834601610013,0.7324718520204072,0.7251293616061326

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2a45ead42d4d9607b7807bd71ea4c3b335b22d91a8ab43a522e860832a35b9
+size 4800552016

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cd2d8a8f10390c66425497723200f5092f4da2760e0f99f4a96496d32fc34a
+size 4767490584

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83cd22ceb6a857e8af881204a63d234470f4476afa61d017c67dfd32371bc19
+size 4834139704

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccebe18d649e3b7a03bd3cf83be1436c37e53cac7bb1b01ad40869140a18ccd
+size 4767490664

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85cf0537c23ad0c1c9c3b1042ece0debaf9a4da0daf822a93854e19e08af2ffc
+size 4834139704

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fe108de4d049f4e3ccd2971631588ef4c5779d15afc151ff2252298e82ad4f
+size 4767490664

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832f45c988b195da0b67bcc39793a0493fdf097be569ba8e7dd8593ef5945710
+size 4834139704

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec04e653e03a55e81c55d7d836e6a9763c77a6ff9c81a35e2af90685c9136c0
+size 4767490664

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84baad34441e04d236591b89d0d6682eebdf86fce5e41fff04b0dc96ad4439a5
+size 4196194808

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/model.safetensors.index.json

@@ -0,0 +1,633 @@
+{
+  "metadata": {
+    "total_size": 42569056256
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.q_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.v_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.q_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.v_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.q_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.v_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.q_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.v_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.q_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.v_proj.base_layer.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00009.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.q_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.v_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.q_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.v_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.q_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.v_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.q_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.v_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.q_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.v_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.q_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.v_proj.base_layer.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00009.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.q_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.v_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.q_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.v_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.q_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.v_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.q_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.v_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.q_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.v_proj.base_layer.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00009.safetensors",
+    "layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.q_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.v_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.q_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.v_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.q_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.v_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.q_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.v_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.q_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.v_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.q_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.v_proj.base_layer.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00009.safetensors",
+    "layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.q_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.v_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.q_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.v_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.q_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.v_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.q_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.v_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.37.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.q_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.v_proj.base_layer.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00009.safetensors",
+    "layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.q_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.v_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.39.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.q_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.v_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00009.safetensors",
+    "layers.40.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.q_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.v_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.41.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.q_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.v_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.42.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.q_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.v_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.43.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.q_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.v_proj.base_layer.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00009.safetensors",
+    "layers.44.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.q_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.v_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.45.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.q_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.v_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.46.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.q_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.v_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.47.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.q_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.v_proj.base_layer.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00009.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.q_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.v_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.q_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.v_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.q_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.v_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.q_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.v_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.q_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00009.safetensors",
+    "norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 4096,
+  "do_lower_case": false
+}

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "_",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

korsts-eunyounglee-EEVE-LLM2Vec-MNTP-1-2024-04-30_15-35-57/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28730": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "mask_token": "_",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

mlm/Llama-2-7b-chat-hf/README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.4.0

mlm/Llama-2-7b-chat-hf/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "auto_mapping": {
+    "base_model_class": "LlamaBiModel",
+    "parent_library": "llm2vec.models.bidirectional_llama"
+  },
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": null
+}

mlm/Llama-2-7b-chat-hf/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596b9c4538a701ac0ea126d700d1361cc09c6d858536fa8571d107c9bc881164
+size 160067146

mlm/Llama-2-7b-chat-hf/all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.04872194321280853,
+    "eval_loss": 1.640622615814209,
+    "eval_runtime": 153.2894,
+    "eval_samples": 2726,
+    "eval_samples_per_second": 17.783,
+    "eval_steps_per_second": 0.561,
+    "perplexity": 5.158380201707228,
+    "train_loss": 2.499020125514777,
+    "train_runtime": 1862.6283,
+    "train_samples": 2726,
+    "train_samples_per_second": 4.391,
+    "train_steps_per_second": 0.139
+}

mlm/Llama-2-7b-chat-hf/checkpoint-200/README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.4.0

mlm/Llama-2-7b-chat-hf/checkpoint-200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "auto_mapping": {
+    "base_model_class": "LlamaBiModel",
+    "parent_library": "llm2vec.models.bidirectional_llama"
+  },
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": null
+}

mlm/Llama-2-7b-chat-hf/checkpoint-200/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ac7e3228a77dcb65353aea3ef04dc4a1cf43db60ed19ee995e3d75bc26c591
+size 160067146

mlm/Llama-2-7b-chat-hf/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104b9fa0192273227aa12b15b51da0027f1e73be11efca4b1537b025a3f8fc22
+size 844482901

mlm/Llama-2-7b-chat-hf/checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44cb46a508839e226a470e9197c5475cecea23d8d0ec5729aac2e043bf94792
+size 14244

mlm/Llama-2-7b-chat-hf/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7815deb57c650b935dfad21a71229383faca596ddc73516101da60176c904286
+size 1064

mlm/Llama-2-7b-chat-hf/checkpoint-200/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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
+  },
+  "mask_token": "_",
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

mlm/Llama-2-7b-chat-hf/checkpoint-200/tokenizer.model

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

mlm/Llama-2-7b-chat-hf/checkpoint-200/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "mask_token": "_",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

mlm/Llama-2-7b-chat-hf/checkpoint-200/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3255813953488373,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.16,
+      "eval_accuracy": 0.057827865285875905,
+      "eval_loss": 2.194674253463745,
+      "eval_runtime": 153.2158,
+      "eval_samples_per_second": 17.792,
+      "eval_steps_per_second": 0.561,
+      "step": 100
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.05121255660048764,
+      "eval_loss": 1.6989564895629883,
+      "eval_runtime": 152.7214,
+      "eval_samples_per_second": 17.849,
+      "eval_steps_per_second": 0.563,
+      "step": 200
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 258,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "total_flos": 1.2962977080252826e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

mlm/Llama-2-7b-chat-hf/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bd310094889d4125bbfb313521c0f23ef76f2f22d2d10f81f9b5a89dbdfd93
+size 4984

mlm/Llama-2-7b-chat-hf/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.04872194321280853,
+    "eval_loss": 1.640622615814209,
+    "eval_runtime": 153.2894,
+    "eval_samples": 2726,
+    "eval_samples_per_second": 17.783,
+    "eval_steps_per_second": 0.561,
+    "perplexity": 5.158380201707228
+}

mlm/Llama-2-7b-chat-hf/runs/Apr24_09-48-39_ml-dev-02/events.out.tfevents.1713920037.ml-dev-02.711173.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d25a137575631ea8bfa87c4d649475cec85fcbf3bc35355f6842dbdcfa90911
+size 4791

mlm/Llama-2-7b-chat-hf/runs/Apr24_09-58-24_ml-dev-02/events.out.tfevents.1713920564.ml-dev-02.714158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b4e10842c880e041a0dc66e4aae118d3894e6e862979a0a605075905db9e43
+size 4791

mlm/Llama-2-7b-chat-hf/runs/Apr24_10-46-46_ml-dev-02/events.out.tfevents.1713923281.ml-dev-02.727661.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5344877f933040328543928e2a68b375357228941c75d52487e3f484d2f996db
+size 4715

mlm/Llama-2-7b-chat-hf/runs/Apr25_11-55-00_ml-dev-02/events.out.tfevents.1714013789.ml-dev-02.1360287.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7f9d546c5307e2f1ec7afef078aa327e881f091b2d5e5a54db057a67f0ee1d
+size 5709

mlm/Llama-2-7b-chat-hf/runs/Apr25_11-55-00_ml-dev-02/events.out.tfevents.1714015805.ml-dev-02.1360287.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3b540b39d990fe7549305ae81af7ea381ef9a21682498d03f9c6141dbb2424
+size 411

mlm/Llama-2-7b-chat-hf/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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
+  },
+  "mask_token": "_",
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

mlm/Llama-2-7b-chat-hf/tokenizer.model

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

mlm/Llama-2-7b-chat-hf/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "mask_token": "_",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

mlm/Llama-2-7b-chat-hf/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.499020125514777,
+    "train_runtime": 1862.6283,
+    "train_samples": 2726,
+    "train_samples_per_second": 4.391,
+    "train_steps_per_second": 0.139
+}

mlm/Llama-2-7b-chat-hf/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 258,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.16,
+      "eval_accuracy": 0.057827865285875905,
+      "eval_loss": 2.194674253463745,
+      "eval_runtime": 153.2158,
+      "eval_samples_per_second": 17.792,
+      "eval_steps_per_second": 0.561,
+      "step": 100
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.05121255660048764,
+      "eval_loss": 1.6989564895629883,
+      "eval_runtime": 152.7214,
+      "eval_samples_per_second": 17.849,
+      "eval_steps_per_second": 0.563,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "step": 258,
+      "total_flos": 1.66999411723862e+17,
+      "train_loss": 2.499020125514777,
+      "train_runtime": 1862.6283,
+      "train_samples_per_second": 4.391,
+      "train_steps_per_second": 0.139
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 258,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "total_flos": 1.66999411723862e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

mlm/Llama-2-7b-chat-hf/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bd310094889d4125bbfb313521c0f23ef76f2f22d2d10f81f9b5a89dbdfd93
+size 4984