Upload folder using huggingface_hub

README.md

@@ -1,3 +1,199 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- 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 [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- 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 Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## 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]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

chat_template.jinja

@@ -1 +1 @@
-{% set image_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|image_pad|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|image_pad|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}

config.json

@@ -1,7 +1,9 @@
 {
   "architectures": [
-    "LoocrForConditionalGeneration"
+    "LightOnOCRForConditionalGeneration"
   ],
+  "dtype": "float32",
+  "image_token_id": 151655,
   "model_type": "mistral3",
   "multimodal_projector_bias": false,
   "projector_hidden_act": "gelu",
@@ -10,26 +12,58 @@
     "architectures": [
       "Qwen3ForCausalLM"
     ],
+    "attention_bias": false,
     "attention_dropout": 0,
     "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 1024,
     "initializer_range": 0.02,
     "intermediate_size": 3072,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
     "max_position_embeddings": 40960,
+    "max_window_layers": 28,
     "model_type": "qwen3",
     "num_attention_heads": 16,
     "num_hidden_layers": 28,
     "num_key_value_heads": 8,
     "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
     "rope_theta": 1000000,
     "sliding_window": null,
     "use_cache": true,
     "use_sliding_window": false,
     "vocab_size": 151936
   },
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.50.0.dev0",
+  "transformers_version": "4.57.0.dev0",
   "vision_config": {
     "attention_dropout": 0,
     "head_dim": 64,
@@ -45,6 +79,5 @@
     "patch_size": 14,
     "rope_theta": 10000
   },
-  "vision_feature_layer": -1,
-  "image_token_index": 151655
-}
+  "vision_feature_layer": -1
+}

generation_config.json

@@ -1,6 +1,13 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "transformers_version": "4.52.4"
+    "bos_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "pad_token_id": 151643,
+    "temperature": 0.2,
+    "top_k": 0,
+    "top_p": 0.9,
+    "transformers_version": "4.55.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3f16419f9f2ec2e9642ff634c6feec49d4825a99a7a526136593df14a35612
-size 2322531488
+oid sha256:c588f8ef5e616dea80f0cb57cf9e82725d98571fdbce3e1e7f507859bb8140d7
+size 2322532696

preprocessor_config.json

@@ -7,6 +7,7 @@
   "do_center_crop": null,
   "do_convert_rgb": true,
   "do_normalize": true,
+  "do_pad": null,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
@@ -21,8 +22,9 @@
     0.27577711
   ],
   "input_data_format": null,
+  "pad_size": null,
   "patch_size": 14,
-  "processor_class": "PixtralProcessor",
+  "processor_class": "LightOnOCRProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "return_tensors": null,

processor_config.json

@@ -3,6 +3,6 @@
   "image_end_token": "<|vision_end|>",
   "image_token": "<|image_pad|>",
   "patch_size": 14,
-  "processor_class": "PixtralProcessor",
+  "processor_class": "LightOnOCRProcessor",
   "spatial_merge_size": 2
-}
+}

tokenizer_config.json

@@ -233,6 +233,7 @@
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
+  "processor_class": "LightOnOCRProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null