Uploading model files

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
+}

README.md

@@ -0,0 +1,142 @@
+---
+language: []
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+widget: []
+---
+
+# SentenceTransformer
+
+This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 4096-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 4096 tokens
+- **Output Dimensionality:** 4096 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 4096, 'do_lower_case': False}) with Transformer model: MistralBiDirectionalModel 
+  (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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 4096]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.11.10
+- Sentence Transformers: 3.0.0
+- Transformers: 4.37.2
+- PyTorch: 2.2.0+cu121
+- Accelerate: 0.34.2
+- Datasets: 3.0.1
+- Tokenizers: 0.15.2
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

bidirectional_models.py

@@ -0,0 +1,171 @@
+from transformers import AutoConfig, AutoModel
+from transformers.models.mistral.configuration_mistral import MistralConfig
+from transformers.models.mistral.modeling_mistral import MistralModel
+
+from typing import List, Optional, Tuple, Union
+import torch
+import torch.nn.functional as F
+from torch import nn
+from torch.nn import CrossEntropyLoss
+
+#from transformers.models.mistral.modeling_mistral import MistralConfig, MistralModel, 
+from transformers.modeling_attn_mask_utils import _prepare_4d_attention_mask_for_sdpa, _prepare_4d_attention_mask
+from transformers.cache_utils import Cache, DynamicCache
+from transformers.modeling_outputs import BaseModelOutputWithPast
+from transformers.utils import (
+    logging
+)
+
+logger = logging.get_logger(__name__)
+
+class MistralBiDirectionalConfig(MistralConfig):
+    model_type = 'mistralbidirectional'
+
+class MistralBiDirectionalModel(MistralModel):
+    config_class = MistralBiDirectionalConfig
+    
+    def __init__(self, config: MistralConfig):
+        super().__init__(config)
+        for layer in self.layers:
+            layer.self_attn.is_causal = False
+        self._attn_implementation = "eager"
+    
+    def forward(
+        self,
+        input_ids: torch.LongTensor = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[List[torch.FloatTensor]] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPast]:
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        use_cache = use_cache if use_cache is not None else self.config.use_cache
+
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        # retrieve input_ids and inputs_embeds
+        if input_ids is not None and inputs_embeds is not None:
+            raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time")
+        elif input_ids is not None:
+            batch_size, seq_length = input_ids.shape
+        elif inputs_embeds is not None:
+            batch_size, seq_length, _ = inputs_embeds.shape
+        else:
+            raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds")
+
+        if self.gradient_checkpointing and self.training:
+            if use_cache:
+                logger.warning_once(
+                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
+                )
+                use_cache = False
+
+        past_key_values_length = 0
+
+        if use_cache:
+            use_legacy_cache = not isinstance(past_key_values, Cache)
+            if use_legacy_cache:
+                past_key_values = DynamicCache.from_legacy_cache(past_key_values)
+            past_key_values_length = past_key_values.get_usable_length(seq_length)
+
+        if position_ids is None:
+            device = input_ids.device if input_ids is not None else inputs_embeds.device
+            position_ids = torch.arange(
+                past_key_values_length, seq_length + past_key_values_length, dtype=torch.long, device=device
+            )
+            position_ids = position_ids.unsqueeze(0).view(-1, seq_length)
+        else:
+            position_ids = position_ids.view(-1, seq_length).long()
+
+        if inputs_embeds is None:
+            inputs_embeds = self.embed_tokens(input_ids)
+
+        # TODO: make sure to pass correct attention_mask if you use cache and flash_attention_2
+        if attention_mask is not None and self._attn_implementation == "flash_attention_2" and use_cache:
+            is_padding_right = attention_mask[:, -1].sum().item() != batch_size
+            if is_padding_right:
+                raise ValueError(
+                    "You are attempting to perform batched generation with padding_side='right'"
+                    " this may lead to unexpected behaviour for Flash Attention version of Mistral. Make sure to "
+                    " call `tokenizer.padding_side  = 'left'` before tokenizing the input. "
+                )
+        original_attention_mask = attention_mask
+        if self._attn_implementation == "flash_attention_2":
+            # 2d mask is passed through the layers
+            attention_mask = attention_mask if (attention_mask is not None and 0 in attention_mask) else None
+            raise Exception("bi-directional maks is not implemented for flash attention 2")
+        elif self._attn_implementation == "sdpa" and not output_attentions:
+            bidirectional_attention_mask = _prepare_4d_attention_mask_for_sdpa(
+                original_attention_mask,
+                inputs_embeds.dtype
+            )
+        else:
+            bidirectional_attention_mask = _prepare_4d_attention_mask(
+                original_attention_mask,
+                inputs_embeds.dtype
+            )
+
+        hidden_states = inputs_embeds
+
+        # decoder layers
+        all_hidden_states = () if output_hidden_states else None
+        all_self_attns = () if output_attentions else None
+        next_decoder_cache = None
+
+        for decoder_layer in self.layers:
+            if output_hidden_states:
+                all_hidden_states += (hidden_states,)
+
+            if self.gradient_checkpointing and self.training:
+                layer_outputs = self._gradient_checkpointing_func(
+                    decoder_layer.__call__,
+                    hidden_states,
+                    bidirectional_attention_mask,
+                    position_ids,
+                    past_key_values,
+                    output_attentions,
+                    use_cache,
+                )
+            else:
+                layer_outputs = decoder_layer(
+                    hidden_states,
+                    attention_mask=bidirectional_attention_mask,
+                    position_ids=position_ids,
+                    past_key_value=past_key_values,
+                    output_attentions=output_attentions,
+                    use_cache=use_cache,
+                )
+
+            hidden_states = layer_outputs[0]
+
+            if use_cache:
+                next_decoder_cache = layer_outputs[2 if output_attentions else 1]
+
+            if output_attentions:
+                all_self_attns += (layer_outputs[1],)
+
+        hidden_states = self.norm(hidden_states)
+
+        # add hidden states from the last decoder layer
+        if output_hidden_states:
+            all_hidden_states += (hidden_states,)
+
+        next_cache = None
+        if use_cache:
+            next_cache = next_decoder_cache.to_legacy_cache() if use_legacy_cache else next_decoder_cache
+
+        if not return_dict:
+            return tuple(v for v in [hidden_states, next_cache, all_hidden_states, all_self_attns] if v is not None)
+        return BaseModelOutputWithPast(
+            last_hidden_state=hidden_states,
+            past_key_values=next_cache,
+            hidden_states=all_hidden_states,
+            attentions=all_self_attns,
+        )

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "nvidia/NV-EmbedCode-7b-v1",
+  "architectures": [
+    "MistralBiDirectionalModel"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "bidirectional_models.MistralBiDirectionalConfig",
+    "AutoModel": "bidirectional_models.MistralBiDirectionalModel"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistralbidirectional",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.37.2",
+    "pytorch": "2.2.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fa665441f5d5146229e6ba30c9900060e652d6c5fc3549778ac7b017066a69
+size 4987196648

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0725c1fd085ef6834d57850266b4a5bad3fe20c23b7c6e96d20fdc674976d1d9
+size 4899116152

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a46f14ef742551f9186862260eb5fe7be1c5f4d263ea3dfbd061730d6c9249
+size 4999812808

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d113a3619813f0b2f198c5794c2d4a51a3fb59d22664d8e5558ccddb6f3bb8cb
+size 4999812808

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44b7d205a94f9de16fa59acfe5b6b6470912304fd88dcf40143486fd7fffdba
+size 4832007216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624ea48c4a385ddafd3420d558bb2071b1cb54e6951c6e6d36414bb9056adf52
+size 3724726552

model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+  "metadata": {
+    "total_size": 28442640384
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

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"
+  }
+]

sentence_bert_config.json

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

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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}