{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"hn-46933515","slug":"fine-tuned-qwen2-5-7b-on-100-films-for-probabilist","name":"Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs","type":"finetune","url":"https://cinegraphs.ai/","page_url":"https://unfragile.ai/fine-tuned-qwen2-5-7b-on-100-films-for-probabilist","categories":["model-training"],"tags":["hackernews","show-hn"],"pricing":{"model":"unknown","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"hn-46933515__cap_0","uri":"capability://planning.reasoning.probabilistic.story.graph.generation","name":"probabilistic story graph generation","description":"This capability generates probabilistic story graphs by leveraging a fine-tuned Qwen2.5-7B model that has been specifically trained on a dataset of 100 films. It utilizes a transformer architecture to understand narrative structures and relationships between characters and events, allowing it to output complex story arcs based on learned probabilities. The model's training on diverse cinematic narratives enables it to capture a wide range of storytelling techniques and styles, making it distinct in its ability to produce nuanced and varied story graphs.","intents":["How can I generate a story graph based on a specific film's narrative?","What are the possible character interactions in a given story?","Can I visualize the relationships between different plot points in a film?"],"best_for":["screenwriters looking to outline scripts","game developers designing narrative-driven experiences","educators teaching storytelling techniques"],"limitations":["Limited to the narratives of the 100 films used for training, which may not generalize well to all genres.","Output complexity may vary based on the input film's narrative structure."],"requires":["Python 3.8+","Access to the Qwen2.5-7B model weights"],"input_types":["text (film scripts, summaries)","structured data (character lists, plot points)"],"output_types":["structured data (story graphs)","visual representations (graph formats)"],"categories":["planning-reasoning","storytelling-tools"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hn-46933515__cap_1","uri":"capability://data.processing.analysis.character.relationship.mapping","name":"character relationship mapping","description":"This capability maps relationships between characters in a story by analyzing dialogue and interactions within the context of the trained films. It employs natural language processing techniques to identify and categorize interactions, allowing users to visualize how characters influence each other's arcs. This mapping is probabilistic, meaning it can suggest potential relationship dynamics based on learned patterns from the training data, providing a unique perspective on character development.","intents":["How can I visualize character dynamics in my screenplay?","What are the potential relationships between characters in a narrative?","Can I analyze how character interactions evolve throughout a story?"],"best_for":["screenwriters wanting to refine character arcs","narrative analysts studying character interactions","game designers crafting character-driven stories"],"limitations":["Accuracy depends on the quality of the input text; poorly written scripts may yield less reliable mappings.","Limited to the character sets present in the training films."],"requires":["Python 3.8+","Access to the Qwen2.5-7B model weights"],"input_types":["text (scripts, dialogues)","structured data (character profiles)"],"output_types":["structured data (relationship maps)","visual representations (network graphs)"],"categories":["data-processing-analysis","character-development-tools"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hn-46933515__cap_2","uri":"capability://planning.reasoning.narrative.arc.prediction","name":"narrative arc prediction","description":"This capability predicts potential narrative arcs by analyzing the structure and flow of stories within the training dataset. It employs machine learning techniques to identify common patterns and tropes in storytelling, allowing it to suggest plausible future events or twists based on the established narrative. This predictive modeling is grounded in the probabilistic nature of the training data, making it capable of generating varied outcomes that align with typical storytelling conventions.","intents":["How can I predict the next plot twist in my story?","What are common narrative arcs for a specific genre?","Can I generate alternative endings for my screenplay?"],"best_for":["screenwriters exploring plot development","game developers designing branching narratives","storytellers seeking inspiration for plot twists"],"limitations":["Predictions are based on learned patterns and may not always align with user intent or originality.","Limited to the narrative structures present in the training dataset."],"requires":["Python 3.8+","Access to the Qwen2.5-7B model weights"],"input_types":["text (story outlines, summaries)","structured data (plot points)"],"output_types":["structured data (predicted arcs)","text (alternative endings)"],"categories":["planning-reasoning","story-development-tools"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":42,"verified":false,"data_access_risk":"low","permissions":["Python 3.8+","Access to the Qwen2.5-7B model weights"],"failure_modes":["Limited to the narratives of the 100 films used for training, which may not generalize well to all genres.","Output complexity may vary based on the input film's narrative structure.","Accuracy depends on the quality of the input text; poorly written scripts may yield less reliable mappings.","Limited to the character sets present in the training films.","Predictions are based on learned patterns and may not always align with user intent or originality.","Limited to the narrative structures present in the training dataset.","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.7,"quality":0.16,"ecosystem":0.21000000000000002,"match_graph":0.25,"freshness":0.9,"weights":{"adoption":0.35,"quality":0.2,"ecosystem":0.1,"match_graph":0.3,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:23.326Z","last_scraped_at":"2026-05-04T08:10:08.734Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=fine-tuned-qwen2-5-7b-on-100-films-for-probabilist","compare_url":"https://unfragile.ai/compare?artifact=fine-tuned-qwen2-5-7b-on-100-films-for-probabilist"}},"signature":"cKfghM5XfC/1mpEaw5fcxvkfVV8DJdaXL3wfleu2y18RPjonj6wzVcOgAiy+W1n928l6VUWsULr+9V0kN6D1Cg==","signedAt":"2026-06-15T08:25:23.670Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/fine-tuned-qwen2-5-7b-on-100-films-for-probabilist","artifact":"https://unfragile.ai/fine-tuned-qwen2-5-7b-on-100-films-for-probabilist","verify":"https://unfragile.ai/api/v1/verify?slug=fine-tuned-qwen2-5-7b-on-100-films-for-probabilist","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}