Push model using huggingface_hub.

1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 1024,
+    "pooling_mode": "mean",
+    "include_prompt": true
+}

2_Normalize/config.json

@@ -0,0 +1,4 @@
+{
+    "module_input_name": "sentence_embedding",
+    "module_output_name": "sentence_embedding"
+}

README.md

@@ -0,0 +1,181 @@
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget: []
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: setfit
+inference: true
+base_model: Hcompany/NeoMME-260M-Retriever-ST-dense
+---
+
+# SetFit with Hcompany/NeoMME-260M-Retriever-ST-dense
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [Hcompany/NeoMME-260M-Retriever-ST-dense](https://huggingface.co/Hcompany/NeoMME-260M-Retriever-ST-dense) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+
+The model has been trained using an efficient few-shot learning technique that involves:
+
+1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
+2. Training a classification head with features from the fine-tuned Sentence Transformer.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SetFit
+- **Sentence Transformer body:** [Hcompany/NeoMME-260M-Retriever-ST-dense](https://huggingface.co/Hcompany/NeoMME-260M-Retriever-ST-dense)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 16384 tokens
+- **Number of Classes:** 6 classes
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
+- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
+- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
+
+### Model Labels
+| Label                 | Examples                                                                                                                                                                                                                                                                          |
+|:----------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| instruction_reference | <ul><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091E4B0></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091F620></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091F620></li></ul> |
+| news_promotion        | <ul><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091FB90></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=800x566 at 0x2ADC0091CE90></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=570x800 at 0x2ADC0091E630></li></ul> |
+| exercise_assessment   | <ul><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=566x800 at 0x2ADC0091E180></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091FB90></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=566x800 at 0x2ADC0091E630></li></ul> |
+| administration_policy | <ul><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091E750></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=566x800 at 0x2ADC0091F7D0></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091E4B0></li></ul> |
+| research_analysis     | <ul><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091CCE0></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091F7D0></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=608x800 at 0x2ADC0091CCE0></li></ul> |
+| other                 | <ul><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091E630></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091D5E0></li><li><PIL.PngImagePlugin.PngImageFile image mode=RGB size=619x800 at 0x2ADC0091D5E0></li></ul> |
+
+## Uses
+
+### Direct Use for Inference
+
+First install the SetFit library:
+
+```bash
+pip install setfit
+```
+
+Then you can load this model and run inference.
+
+```python
+from PIL import Image
+
+from setfit import SetFitModel
+
+# Download from the 🤗 Hub
+model = SetFitModel.from_pretrained("oneryalcin/finepdfs-purpose-setfit-neomme-v2")
+# Run inference on images
+preds = model([Image.open("example.png")])
+```
+
+<!--
+### Downstream Use
+
+*List how someone could finetune this model on their own dataset.*
+-->
+
+<!--
+### 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
+
+### Training Hyperparameters
+- batch_size: (32, 32)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 3
+- body_learning_rate: (2e-05, 1e-05)
+- head_learning_rate: 0.01
+- loss: CosineSimilarityLoss
+- distance_metric: cosine_distance
+- margin: 0.25
+- end_to_end: False
+- use_amp: False
+- warmup_proportion: 0.1
+- l2_weight: 0.01
+- seed: 42
+- eval_max_steps: -1
+- load_best_model_at_end: False
+
+### Training Results
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0014 | 1    | 0.2760        | -               |
+| 0.0686 | 50   | 0.2481        | -               |
+| 0.1372 | 100  | 0.2100        | -               |
+| 0.2058 | 150  | 0.1900        | -               |
+| 0.2743 | 200  | 0.1748        | -               |
+| 0.3429 | 250  | 0.1622        | -               |
+| 0.4115 | 300  | 0.1531        | -               |
+| 0.4801 | 350  | 0.1388        | -               |
+| 0.5487 | 400  | 0.1345        | -               |
+| 0.6173 | 450  | 0.1241        | -               |
+| 0.6859 | 500  | 0.1158        | -               |
+| 0.7545 | 550  | 0.1059        | -               |
+| 0.8230 | 600  | 0.0968        | -               |
+| 0.8916 | 650  | 0.0840        | -               |
+| 0.9602 | 700  | 0.0874        | -               |
+
+### Framework Versions
+- Python: 3.12.10
+- SetFit: 1.3.0.dev0
+- Sentence Transformers: 6.0.1
+- Transformers: 5.17.0
+- PyTorch: 2.14.0+cu130
+- Datasets: 5.0.1
+- Tokenizers: 0.23.2
+
+## Citation
+
+### BibTeX
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+    doi = {10.48550/ARXIV.2209.11055},
+    url = {https://arxiv.org/abs/2209.11055},
+    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+    title = {Efficient Few-Shot Learning Without Prompts},
+    publisher = {arXiv},
+    year = {2022},
+    copyright = {Creative Commons Attribution 4.0 International}
+}
+```
+
+<!--
+## 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.*
+-->

chat_template.jinja

@@ -0,0 +1,67 @@
+{#-
+    NeoMME retrieval prompt template. Not a conversation format: NeoMME is an encoder and has no chat turns.
+
+    `task` selects the retrieval side. A sentence-transformers v6 `MultiVectorEncoder` routes
+    `task="query"` / `task="document"` here when the template declares the variable.
+
+      task="query"     ->  <query> … N x <mask>       ColBERT-style learned query expansion. <mask> is the
+                                                      masked-diffusion fill token. The exporter sets N from the
+                                                      checkpoint.
+      task="document"  ->  <doc> …                    Text passages. Image pages take the same <doc> prefix
+                                                      followed by one image token placeholder, which the processor
+                                                      expands after it knows the patch grid.
+-#}
+{%- if task is not defined -%}
+    {{- raise_exception("NeoMME chat templates require task='query' or task='document'.") -}}
+{%- endif -%}
+{%- if task not in ['query', 'document'] -%}
+    {{- raise_exception("task=" ~ task ~ " is not supported: expected 'query' or 'document'.") -}}
+{%- endif -%}
+{%- if messages is not defined or not messages -%}
+    {{- raise_exception("NeoMME chat conversations must contain at least one message.") -}}
+{%- endif -%}
+
+{# Collect content and validate one retrieval item without imposing batch-level policy. #}
+{%- set state = namespace(text='', has_text=false, image_count=0) -%}
+{%- for message in messages -%}
+    {%- set content = message.content -%}
+    {%- set items = [{'type': 'text', 'text': content}] if content is string else content -%}
+    {%- for item in items -%}
+        {%- if item.type == 'text' -%}
+            {%- if image_token in item.text -%}
+                {{- raise_exception(image_token ~ " is reserved for image documents.") -}}
+            {%- endif -%}
+            {%- set state.has_text = true -%}
+            {%- set state.text = state.text + item.text -%}
+        {%- elif item.type == 'image' -%}
+            {%- if item.image is not defined or item.image is none or item.image == '' -%}
+                {{- raise_exception("NeoMME image content must provide an image source.") -}}
+            {%- endif -%}
+            {%- set state.image_count = state.image_count + 1 -%}
+        {%- elif item.type == 'image_url' -%}
+            {%- if item.image_url is not defined or not item.image_url -%}
+                {{- raise_exception("NeoMME image_url content must provide an image source.") -}}
+            {%- endif -%}
+            {%- set state.image_count = state.image_count + 1 -%}
+        {%- else -%}
+            {{- raise_exception("NeoMME chat templates do not support content type " ~ item.type ~ ".") -}}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endfor -%}
+
+{%- if state.image_count and state.has_text -%}
+    {{- raise_exception("NeoMME cannot encode text and images in the same conversation.") -}}
+{%- endif -%}
+{%- if state.image_count > 1 -%}
+    {{- raise_exception("NeoMME accepts one image document per conversation.") -}}
+{%- endif -%}
+{%- if state.image_count and task != 'document' -%}
+    {{- raise_exception("NeoMME image content must use task='document'.") -}}
+{%- endif -%}
+
+{%- set content = image_token if state.image_count else state.text -%}
+{%- if task == 'query' -%}
+    {{- query_token + content + mask_token * 10 -}}
+{%- else -%}
+    {{- document_token + content -}}
+{%- endif -%}

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "NeoMMEModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "document_token_id": 5,
+  "dtype": "float32",
+  "embedding_dim": 128,
+  "embedding_rank": 256,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "relu2",
+  "hidden_size": 1024,
+  "image_token_id": 6,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "neomme",
+  "norm_eps": 1e-06,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 17,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "patch_size": 32,
+  "per_layer_config": {
+    "01": {
+      "sliding_window": 1024
+    },
+    "03": {
+      "sliding_window": 1024
+    },
+    "05": {
+      "sliding_window": null
+    },
+    "06": {
+      "sliding_window": 1024
+    },
+    "08": {
+      "sliding_window": 1024
+    },
+    "10": {
+      "sliding_window": 1024
+    },
+    "11": {
+      "sliding_window": null
+    },
+    "13": {
+      "sliding_window": 1024
+    },
+    "15": {
+      "sliding_window": 1024
+    },
+    "16": {
+      "sliding_window": null
+    }
+  },
+  "residual_multiplier": 0.17149858514250885,
+  "rope_parameters": {
+    "full_attention": {
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "partial_rotary_factor": 1.0,
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 256,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.17.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.14.0+cu130",
+    "sentence_transformers": "6.0.1",
+    "transformers": "5.17.0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": ""
+  },
+  "similarity_fn_name": "cosine"
+}

config_setfit.json

@@ -0,0 +1,12 @@
+{
+  "labels": [
+    "administration_policy",
+    "exercise_assessment",
+    "instruction_reference",
+    "news_promotion",
+    "research_analysis",
+    "other"
+  ],
+  "task": "document",
+  "normalize_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fa4931791ea2f35cde3e1a39187695a64e705af1775908ecd6a6d3082b0a3d
+size 1051769336

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b38e87b10d6fca6baa4b212112c8e39df9663a0a13f3f36bbac15632593566
+size 25503

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.base.modules.normalize.Normalize"
+  }
+]

processor_config.json

@@ -0,0 +1,24 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "NeoMMEImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_side": 2048,
+    "patch_size": 32,
+    "resample": 2,
+    "rescale_factor": 0.00392156862745098
+  },
+  "processor_class": "NeoMMEProcessor"
+}

sentence_bert_config.json

@@ -0,0 +1,20 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "image": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "message": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state",
+            "format": "structured"
+        }
+    },
+    "module_output_name": "token_embeddings",
+    "unpad_inputs": false
+}

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "document_token": "<doc>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [],
+  "image_token": "<img>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 16384,
+  "model_specific_special_tokens": {
+    "document_token": "<doc>",
+    "image_token": "<img>",
+    "query_token": "<query>",
+    "row_token": "<row>"
+  },
+  "pad_token": "<pad>",
+  "processor_class": "NeoMMEProcessor",
+  "query_token": "<query>",
+  "row_token": "<row>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}