Upload folder using huggingface_hub

1_TokenPooling/config.json

@@ -0,0 +1,3 @@
+{
+    "dimension": 4096
+}

README.md

@@ -1,199 +1,141 @@
 ---
-library_name: transformers
-tags: []
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# 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 -->
 
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+### Model Sources
 
-### Model Sources [optional]
+- **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)
 
-<!-- Provide the basic links for the model. -->
+### Full Model Architecture
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+```
+SentenceTransformer(
+  (0): Transformer({'model_name_or_path': 'lamarr-llm-development/elbedding'}) with Transformer model: LlamaModel 
+  (1): TokenPooling()
+  (2): Normalize()
+)
+```
 
-## Uses
+## Usage
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Direct Usage (Sentence Transformers)
 
-### Direct Use
+First install the Sentence Transformers library:
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```bash
+pip install -U sentence-transformers
+```
 
-[More Information Needed]
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
 
-### Downstream Use [optional]
+# 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]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
 
-[More Information Needed]
+<!--
+### Direct Usage (Transformers)
 
-### Out-of-Scope Use
+<details><summary>Click to see the direct usage in Transformers</summary>
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+</details>
+-->
 
-[More Information Needed]
+<!--
+### Downstream Usage (Sentence Transformers)
 
-## Bias, Risks, and Limitations
+You can finetune this model on your own dataset.
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+<details><summary>Click to expand</summary>
 
-[More Information Needed]
+</details>
+-->
 
-### Recommendations
+<!--
+### Out-of-Scope Use
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+<!--
+## Bias, Risks and Limitations
 
-## How to Get Started with the Model
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
 
-Use the code below to get started with the model.
+<!--
+### Recommendations
 
-[More Information Needed]
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
 
 ## Training Details
 
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.2.1
+- Transformers: 4.48.3
+- PyTorch: 2.4.0+cu121
+- Accelerate: 1.4.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.0
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+## Citation
 
-[More Information Needed]
+### BibTeX
 
-## More Information [optional]
+<!--
+## Glossary
 
-[More Information Needed]
+*Clearly define terms in order to be accessible across audiences.*
+-->
 
-## Model Card Authors [optional]
+<!--
+## Model Card Authors
 
-[More Information Needed]
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
 
+<!--
 ## Model Card Contact
 
-[More Information Needed]
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,52 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "lamarr-llm-development/elbedding-v2-AutoGPTQ-4bit",
+  "architectures": [
+    "LlamaForSequenceEmbedding"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoTokenizer": [
+      "openGPT-X/Teuken-7B-base-v0.6--gptx_tokenizer.SPTokenizer",
+      null
+    ]
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 4,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.0158,
+  "intermediate_size": 13440,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 2,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "group_size": 128,
+    "is_marlin_format": false,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "tokenizer_class": "SPTokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 250880
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.4.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

modules.json

@@ -0,0 +1,20 @@
+[
+    {
+        "idx": 0,
+        "name": "0",
+        "path": "",
+        "type": "embedding_model.EmbeddingModel"
+    },
+    {
+        "idx": 1,
+        "name": "1",
+        "path": "1_TokenPooling",
+        "type": "token_pooling.TokenPooling"
+    },
+    {
+        "idx": 2,
+        "name": "2",
+        "path": "2_Normalize",
+        "type": "sentence_transformers.models.Normalize"
+    }
+]

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null,
+  "is_marlin_format": false,
+  "quant_method": "gptq"
+}

sentence_bert_config.json

@@ -0,0 +1,3 @@
+{
+    "model_name_or_path": "lamarr-llm-development/elbedding-v2-AutoGPTQ-4bit"
+}

token_pooling.py

@@ -0,0 +1,59 @@
+import json
+import os
+import torch
+import torch.nn as nn
+
+
+class TokenPooling(nn.Module):
+    def __init__(self, dimension: int = 4096) -> None:
+        super(TokenPooling, self).__init__()
+        self.dimension = dimension
+
+    def forward(
+        self, features: dict[str, torch.Tensor], **kwargs
+    ) -> dict[str, torch.Tensor]:
+        token_embeddings = features["token_embeddings"]
+        attention_mask = features["attention_mask"]
+
+        embeddings = self.pool(
+            last_hidden_state=token_embeddings, attention_mask=attention_mask
+        )
+        features["sentence_embedding"] = embeddings
+        return features
+
+    def pool(
+        self, last_hidden_state: torch.Tensor, attention_mask: torch.Tensor
+    ) -> torch.Tensor:
+        """
+        Here, we take the embedding of the last token from the last layer
+        """
+        left_padding = attention_mask[:, -1].sum() == attention_mask.shape[0]
+        if left_padding:
+            return last_hidden_state[:, -1]
+        else:
+            sequence_lengths = attention_mask.sum(dim=1) - 1
+            batch_size = last_hidden_state.shape[0]
+            return last_hidden_state[
+                torch.arange(batch_size, device=last_hidden_state.device).long(),
+                sequence_lengths.long(),
+            ]
+
+    def get_sentence_embedding_dimension(self) -> int:
+        return self.dimension
+
+    def get_config_dict(self) -> dict[str, float]:
+        return {"dimension": self.dimension}
+
+    def save(self, save_dir: str, **kwargs) -> None:
+        pooling_path = os.path.join(save_dir)
+        if not os.path.exists(pooling_path):
+            os.makedirs(pooling_path)
+
+        with open(f"{pooling_path}/config.json", "w+") as f:
+            json.dump(self.get_config_dict(), f, indent=4)
+
+    @staticmethod
+    def load(load_dir: str, **kwargs) -> "TokenPooling":
+        with open(os.path.join(load_dir, "config.json")) as fIn:
+            config = json.load(fIn)
+        return TokenPooling(**config)