Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 license: apache-2.0
 base_model: google/gemma-4-E4B
-pipeline_tag: image-text-to-text
+pipeline_tag: image-text-to-image
 library_name: transformers
 language:
 - en
@@ -21,32 +21,13 @@ datasets:
 metrics:
 - accuracy
 - f1
-# new_version:            # leave unset — only used later to point to a v2 successor
-# --- Eval Results (uncomment and fill once the eval harness produces numbers) ---
-# model-index:
-# - name: opengraph-image-gemma4-e4b-v1
-#   results:
-#   - task:
-#       type: image-text-to-text
-#       name: Image-to-Knowledge-Graph Extraction
-#     dataset:
-#       name: OpenGraph Image Gold v1 (test split)
-#       type: OpenGraphAI/opengraph-image-gold-v1
-#       split: test
-#     metrics:
-#     - type: accuracy
-#       name: Schema-valid extraction rate
-#       value: [XX.X]
-#     - type: f1
-#       name: Node/Edge F1
-#       value: [XX.X]
 ---
 
 # Model Card for opengraph-image-gemma4-e4b-v1
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-A fine-tuned **Gemma 4 E4B** that turns a single image into a valid, schema-faithful **knowledge graph** (`graph.json`) — objects, attributes, scene context, text spans, and the relationships between them — ready for AI agents to query and reason over. Built by [OpenGraph AI](https://github.com/OpenGraphAI/opengraph-ai) as the small, cheap, on-device alternative to calling a frontier vision API for every extraction.
+A fine-tuned **Gemma 4 E4B** that turns images into a valid, schema-faithful **knowledge graph** (`graph.json`) — objects, attributes, scene context, text spans, and the relationships between them — ready for AI agents to query and reason over. Built by [OpenGraph AI](https://github.com/OpenGraphAI/opengraph-ai) as the small, cheap, on-device alternative to calling a frontier vision API for every extraction.
 
 ## Model Details
 
@@ -55,7 +36,7 @@ A fine-tuned **Gemma 4 E4B** that turns a single image into a valid, schema-fait
 The model does one thing extremely well: **image → knowledge graph, on-schema, every time.** It was trained on verified image→graph gold pairs so that its output always conforms to OpenGraph's `graph.json` contract — stable snake_case node IDs with type prefixes (`entity_`, `concept_`, `event_`, `attr_`), typed edges, and cross-image-mergeable entities. Compared to prompting a general frontier model, it is dramatically cheaper per extraction, runs on a single consumer GPU (or laptop, quantized), and produces structurally consistent output that downstream graph tooling can rely on.
 
 - **Developed by:** OpenGraph AI
-- **Model type:** Multimodal (image-text-to-text), decoder-only transformer; QLoRA fine-tune of Gemma 4 E4B
+- **Model type:** Multimodal (image-text-to-image), decoder-only transformer; QLoRA fine-tune of Gemma 4 E4B
 - **Language(s):** English
 - **License:** Apache 2.0 (inherited from Gemma 4; use is additionally subject to Google's [Gemma terms of use](https://ai.google.dev/gemma/terms))
 - **Finetuned from model:** [`google/gemma-4-E4B`](https://huggingface.co/google/gemma-4-E4B)
@@ -63,13 +44,13 @@ The model does one thing extremely well: **image → knowledge graph, on-schema,
 ### Model Sources
 
 - **Repository:** https://github.com/OpenGraphAI/opengraph-ai
-- **Demo:** [More Information Needed] <!-- link the graph.html shareable demo when live -->
+- **Demo:** [placeholder] <!-- link the graph.html shareable demo when live -->
 
 ## Uses
 
 ### Direct Use
 
-Feed the model one image plus the OpenGraph extraction system prompt; it returns a complete `graph.json` — nodes for detected objects (fine-grained labels, normalized bounding boxes), one scene node, attribute nodes, transcribed text spans, and the edges wiring them together. Useful anywhere images need to become structured, queryable knowledge: visual search indexes, dataset annotation, scene understanding, and document/diagram parsing.
+Feed the model images plus the OpenGraph extraction system prompt; it returns a complete `graph.json` — nodes for detected objects (fine-grained labels, normalized bounding boxes), one scene node, attribute nodes, transcribed text spans, and the edges wiring them together. Useful anywhere images need to become structured, queryable knowledge: visual search indexes, dataset annotation, scene understanding, and document/diagram parsing.
 
 ### Downstream Use
 
@@ -143,7 +124,7 @@ Or skip the code entirely and use it through the MCP server:
 
 ### Training Data
 
-Trained on **[More Information Needed — N] verified image→`graph.json` gold pairs** ([`OpenGraphAI/opengraph-image-gold-v1`](https://huggingface.co/datasets/OpenGraphAI/opengraph-image-gold-v1)), assembled from two sources: (1) public scene-graph datasets (e.g., Visual Genome) converted programmatically into the `graph.json` schema, and (2) unannotated images labeled by two independent frontier vision models, auto-accepted where both models agreed and human-reviewed otherwise. Every pair passed the OpenGraph Pydantic schema validators before inclusion.
+Trained on **[placeholder] verified image���`graph.json` gold pairs** ([`OpenGraphAI/opengraph-image-gold-v1`](https://huggingface.co/datasets/OpenGraphAI/opengraph-image-gold-v1)), assembled from two sources: (1) public scene-graph datasets (e.g., Visual Genome) converted programmatically into the `graph.json` schema, and (2) unannotated images labeled by two independent frontier vision models, auto-accepted where both models agreed and human-reviewed otherwise. Every pair passed the OpenGraph Pydantic schema validators before inclusion.
 
 ### Training Procedure
 
@@ -199,15 +180,6 @@ All numbers produced by the open [eval harness](https://github.com/OpenGraphAI/o
 
 [More Information Needed — 2–3 honest sentences: where the fine-tune wins, where it still trails the frontier baseline]
 
-## Environmental Impact
-
-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 — e.g., 1× NVIDIA L4 / A100]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** Google Colab
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
 
 ## Technical Specifications
 
@@ -225,24 +197,10 @@ Gemma 4 E4B: a decoder-only transformer (~4.5B effective parameters, ~8B with em
 
 Python, PyTorch, Hugging Face `transformers>=5.10.1`, `trl`, `peft`, `bitsandbytes`, `datasets`.
 
-## Citation
-
-**BibTeX:**
-
-```bibtex
-@misc{opengraph2026imagegemma,
-  title  = {opengraph-image-gemma4-e4b-v1: A schema-faithful image-to-knowledge-graph model},
-  author = {OpenGraph AI},
-  year   = {2026},
-  url    = {https://huggingface.co/OpenGraphAI/opengraph-image-gemma4-e4b-v1}
-}
-```
-
-This model builds on Gemma 4 — please also cite the [Gemma 4 Technical Report](https://arxiv.org/abs/2607.02770) (Gemma Team, 2026).
 
 ## More Information
 
-OpenGraph AI is open-source, MCP-first infrastructure for turning heterogeneous data (images, tables, text) into semantic knowledge graphs that AI agents can query and reason over. ⭐ [Star the repo](https://github.com/OpenGraphAI/opengraph-ai) — and contribute schemas, test images, or extraction edge cases.
+OpenGraph AI is open-source, MCP-first infrastructure for turning heterogeneous data (images, tables, text, audio, video) into semantic knowledge graphs that AI agents can query and reason over. ⭐ [Star the repo](https://github.com/OpenGraphAI/opengraph-ai) — and contribute schemas, test images, or extraction edge cases.
 
 ## Model Card Authors